Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, indicating write operation. Description adds no further behavioral traits (e.g., whether comment is appended or replaces, required permissions). Annotations carry the burden; description is adequate but adds no extra context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no wasted words. Essential information only. Perfectly concise for this simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given tool simplicity, schema coverage, and annotations, description is nearly complete. Could optionally mention return value, but not required. Adequate for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both params (id, body). Baseline is 3. Description adds no additional meaning beyond what schema provides (e.g., no format hints beyond what's in schema).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'Add a comment' to a specific resource 'Linear issue'. It distinguishes from sibling tools like createLinearIssue (create issue) and fetchLinearIssue (fetch issue) by focusing on adding a comment to an existing issue.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States prerequisite 'Requires Linear connector connected.' Implies when to use: when you want to add a comment to an existing Linear issue. Does not explicitly mention when not to use or alternatives, but sibling names provide differentiation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide destructiveHint: true, so the description need not repeat that. The description does not add further behavioral context (e.g., whether changes are saved), but is adequate given the annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences, front-loading the action and providing prerequisite guidance. Every word earns its place; highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the description covers the basic purpose and prerequisite, it omits details about what happens after applying (e.g., file modification, success/failure feedback). Given the tool's complexity and destructive hint, it could be more complete, but is minimally adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all 6 parameters, so the schema does the heavy lifting. The description adds no extra parameter-level meaning, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool applies a code action by title and explicitly mentions the prerequisite step of using getCodeActions. This distinguishes it from siblings like getCodeActions and previewCodeAction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly advises to use getCodeActions first to see options, providing clear usage guidance. It lacks explicit when-not-to-use instructions but the context is sufficiently clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already indicates no destructive behavior. The description adds that it supports multiple package managers but does not disclose important behavioral details such as what 'auto' means for packageManager or the reserved nature of maxAge (though maxAge is described in the schema).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise, consisting of three short sentences that communicate the core purpose, supported package managers, and relationship to a sibling. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description should at least hint at the output format. It only says 'current vs latest', which is vague. Also, the description does not mention the maxAge parameter's reserved nature, though it is in the schema. Overall, it is adequate but could be more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents both parameters. The description does not add any extra meaning beyond what is in the schema, meeting the baseline for complete schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'detect' and resource 'outdated packages', and distinguishes itself from the sibling 'getSecurityAdvisories' by noting it is a complement. The supported package managers are listed, providing specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions it is a complement to getSecurityAdvisories, providing some guidance on when to use this tool vs that alternative. However, it lacks explicit when-not-to-use instructions or detailed context for other siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description's behavioral claims are limited to the batch limit (up to 10). This adds value but not extensive insight. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no filler. Every part serves a purpose: stating function and providing usage guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the annotation (readOnlyHint), clear schema, and no output schema, the description adequately covers the tool's purpose and when to use it. Could mention return behavior but not essential for agent invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the description reinforces the batch limit. No additional parameter meaning is provided beyond what the schema already covers, meeting the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies the verb 'find' and resource 'implementations', distinguishes from sibling 'findImplementations' by noting batch capability, and adds the constraint 'up to 10 symbols'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Prefer over repeated findImplementations', providing a clear alternative and usage context. Does not include when-not-to-use but the preference is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true. Description adds behavioral detail: returns type signatures and docs, limited to 10 positions. No contradictions. Adds value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose and key constraint. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple batch tool with well-documented schema and no output schema, the description is adequate. Could mention error behavior for individual items, but not necessary for basic usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. Description does not add new parameter-level details beyond what schema already provides, but reinforces the max count.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it provides hover info (type signatures, docs) for up to 10 positions, and explicitly differentiates from repeated getHover by saying 'Prefer over repeated getHover'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises to prefer this over repeated getHover, giving clear usage context. Could be improved by stating when not to use (e.g., for single positions), but the guidance is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, so description doesn't need to add safety info. Description adds the 'up to 10' constraint, but no further behavioral details beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, front-loaded with purpose, no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple with one parameter; description covers the batch limit and usage advice, sufficient for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with full descriptions for each sub-property. Description adds no additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the verb 'Go to definition' and resource 'symbols', and distinguishes from sibling 'goToDefinition' by mentioning batching and preference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Prefer over repeated goToDefinition', indicating when to use this batch variant. Does not explicitly state when not to, but the alternative is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description claims to start a new transaction, a mutation, yet the annotations set readOnlyHint: true. This is a direct contradiction. The description fails to disclose that it creates state, violating behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, no fluff. Front-loads the core action and immediately provides essential follow-up context about the return value and usage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description's mention of returning a transactionId is helpful. However, it lacks details about transaction limits, behavior when a transaction already exists, or error conditions. The contradiction with annotations also undermines completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single optional transactionId parameter, with a clear description in the schema. The tool description adds no extra parameter meaning, but the baseline is adequate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Start a new multi-file edit transaction' – a specific verb and resource. It also mentions the return value and its use with stageEdit, which distinguishes it from related siblings like commitTransaction and rollbackTransaction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly indicates when to use this tool ('before subsequent stageEdit calls'), but does not explicitly state when not to use it or mention alternatives. The context is clear enough for a transaction initiation tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description's 'Health check' aligns. It adds value by listing the specific components checked, which goes beyond the annotation. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no wasted words. The first sentence front-loads the purpose with a colon-separated list, and the second provides usage guidance. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, no-output-schema tool, the description fully covers what the tool does and when to use it. It is complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so the baseline is 4. The description correctly has no parameter details; it is not required. The schema coverage is 100% by nature.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it performs a health check on specific components (extension, git, linters, test runners, GitHub CLI). This is a specific verb+resource combination that distinguishes it from sibling tools like getBridgeStatus, which likely provides a narrower status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use when tools misbehave,' providing clear when-to-use guidance. It does not list exclusions or alternatives, but the context is clear and sufficient for the tool's simplicity.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate idempotentHint=true, and description does not add significant behavioral detail beyond the cancel action. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no fluff, action first.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool is simple with one parameter; description suffices for correct usage without output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single parameter with schema description coverage 100%; description does not add extra meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states action (cancel) and resource (Claude task), distinguishing it from sibling tools like runClaudeTask and resumeClaudeTask.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when or when-not-to-use guidance; however, the tool name and description are self-explanatory for its singular purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, which matches the read-only nature. Description adds that output is base64 PNG and that a display is required. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states purpose and output, second adds platform constraints. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, output format, and constraints. No output schema needed. Could mention resolution or window selection, but not required for basic screenshot.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has no parameters, so schema coverage is 100%. Description does not need to add parameter info, and adds none. Baseline 4 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Capture screenshot → base64 PNG', specifying the verb and resource. Differentiates from sibling 'screenshotAndAnnotate' by not including annotation features, and adds OS/display constraints.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: 'macOS/Linux with display only' and 'Not available on headless servers'. However, it does not explicitly mention when to use this tool versus the sibling 'screenshotAndAnnotate'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description adds valuable behavioral context: the tool uses the VS Code buffer when the extension is connected and a heuristic otherwise. This informs the agent about reliability and dependency on connection status.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with just two sentences. The first sentence states the purpose, and the second adds important implementation detail. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description adequately covers the tool's functionality but does not specify the output format (e.g., returns a boolean). With no output schema, this omission leaves the agent without explicit information on what the tool returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes the single parameter 'filePath' with 100% coverage. The description adds no additional meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Check if file has unsaved changes' with a specific verb and resource. It distinguishes from sibling tools like saveDocument (which writes) and getOpenEditors (which lists open files) by focusing on the dirty check.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the two operation modes (buffer vs heuristic) but does not explicitly state when to use this tool over alternatives like getBufferContent or getGitDiff. The agent must infer usage context from the behavior description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide idempotentHint=true. The description adds context that it clears 'Claude-managed decorations', which clarifies scope. No contradictions, but no further behavioral details like side effects or return values.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words. It efficiently conveys the tool's purpose and parameter behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one optional parameter and no output schema, the description is largely complete. It covers the key behavior and scope, though it could briefly mention the return value (e.g., success indicator).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema documentation covers 100% of the parameter with a clear description. The tool description simply restates the schema, adding no new meaning beyond what the parameter description already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'clear', the resource 'editor decorations', and specifies two modes: clearing by ID or clearing all Claude-managed decorations. It effectively distinguishes from the sibling tool 'setEditorDecorations'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (to clear specific or all decorations) and hints at alternatives via sibling tool names, but does not explicitly state when not to use it or compare to other tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as destructive. The description adds the cleanup of temp directories, which provides some additional context. However, it does not disclose potential side effects like loss of unsaved diff changes or scope of operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that immediately conveys the tool's purpose. No wasted words; it is front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema and only one annotation (destructiveHint), the description covers the main actions. It could clarify scope (e.g., all open diff tabs across workspaces) but is otherwise sufficient for its simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so the description need not explain them. The baseline for 0 parameters is 4, and the description appropriately states the action without unnecessary detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Close all diff tabs and clean up temp diff directories.' It uses specific verbs and resources, distinguishing it from the sibling 'closeTab' tool which closes a single tab.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like 'closeTab'. The purpose is implied by the name and description, but the agent would benefit from explicit context about bulk vs. single tab closure.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate destructiveHint=true, and the description adds that it prompts to save if dirty, which is important behavioral context not captured elsewhere. However, 'Requires ext.' is vague and leaves ambiguity about what extension is needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no unnecessary words. It front-loads the core purpose and provides key behavioral notes. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, the description is reasonably complete. It covers the action, parameter, and a notable behavior (dirty prompt). However, it lacks details on edge cases like if the file is not already open or what 'Requires ext.' entails.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers the single parameter with a clear description. The tool description adds 'by file path', which confirms the param's role, but doesn't provide additional semantic detail beyond what the schema already offers. With 100% coverage, baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'close', the resource 'editor tab', and the identifying mechanism 'by file path'. It also notes behavioral details like prompting to save if dirty. This distinguishes it from siblings like closeAllDiffTabs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when needing to close a specific tab and mentions a prerequisite ('Requires ext.'), but does not explicitly compare to alternatives or state when not to use it. Guidance is minimal.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark destructiveHint=true, and the description adds critical detail about no rollback on partial failure, which is not evident from annotations alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the primary action, and every sentence adds value. No redundant or tangential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with annotations and no output schema, the description fully covers atomicity, partial failure consequences, and references to sibling tool, making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage with a clear description for transactionId. The description does not add extra meaning beyond what the schema provides, so baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool commits staged edits atomically, with a specific verb-resource pair. It distinguishes itself from rollbackTransaction by warning about partial failure behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises using rollbackTransaction to verify before committing to avoid partial failures. Implies correct usage after beginTransaction, but lacks explicit when-not-to-use or alternative tool comparisons.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true. The description lists what is collected but does not disclose additional behaviors like output structure, size limits, or performance implications. Minimal added value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is front-loaded with the action and resource, then lists items. Every word is functional and concise with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple bundling tool with boolean flags and read-only intent, the description adequately covers the purpose. However, given no output schema, a brief note on the output structure would enhance completeness. Still, it is mostly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear boolean parameter descriptions. The tool description does not add further semantics about the parameters, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it collects multiple IDE contexts (active file, diagnostics, diff, editors, handoff note, git status) in one call. Distinct from sibling tools like getGitStatus, getHandoffNote, etc., which individually fetch each piece.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use when needing multiple context items, but does not explicitly guide when to use this tool versus the individual getter tools (e.g., getGitStatus, getHandoffNote). No when-not or alternative guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond the destructiveHint annotation by noting the VS Code vs native fs fallback behavior and the ability to create directories. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two succinct sentences that front-load the main purpose. No unnecessary words; every sentence contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 5 parameters and lack of output schema, the description covers core functionality well. It could mention error conditions or permission needs, but the schema and annotations fill most gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, each parameter already has a clear description. The tool description adds little parameter-specific information beyond confirming directory creation and the fallback mechanism.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a file or directory within the workspace, with a specific verb and resource. It distinguishes from sibling tools like deleteFile, renameFile, editText by focusing on creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives like editText for existing files or overwrite scenarios. It provides no when-not-to-use or prerequisite guidance, though the schema partially covers overwrite behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond annotations by specifying that it returns the created issue identifier and URL. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no wasted words, front-loading the action and key requirement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 5 parameters, no output schema, and minimal annotations, the description adequately covers the return value and prerequisite. Could mention description format but schema covers it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed parameter descriptions; the tool description adds no further semantics, so baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a new Linear issue, and siblings like fetchLinearIssue, updateLinearIssue differentiate it effectively.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Mentions the prerequisite 'Requires Linear connector connected' but does not provide guidance on when to use this tool versus alternatives like updateLinearIssue or fetchLinearIssue.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist. The description omits critical behavioral details like whether it overwrites or errors if the file already exists, and does not mention permissions or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that conveys the core purpose efficiently with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and no annotations, the description is too brief. It fails to explain return values, error conditions, or behavior on file conflict, leaving the agent underinformed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents parameters. The description adds minimal context about the default filename and workspace root, but does not expand on parameter usage beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a .claude-plan.md file in the workspace root with markdown sections and task checklists, distinguishing it from siblings like updatePlan or deletePlan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as updatePlan for modifications or listPlans for viewing existing plans.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The destructiveHint annotation suggests possible destructive behavior, but the description does not elaborate on implications (e.g., whether creation overwrites existing terminals). Adds no value beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence is concise but sacrifices clarity and accuracy. Could be improved by listing actual parameters or noting defaults.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 4 parameters, no output schema, and a minimal description, the tool lacks important context such as parameter defaults, constraints (cwd must be within workspace), and behavior on conflicts.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with descriptions. The description adds a misleading 'shell' option not in schema and omits the 'show' parameter, causing confusion about available inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool creates a VS Code integrated terminal, distinguishing it from sibling tools like disposeTerminal and listTerminals. However, it inaccurately lists 'shell' as an option not present in the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives (e.g., sendTerminalCommand, waitForTerminalOutput). Does not mention prerequisites or context for use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so no destructive behavior. Description adds key behavioral context: auto-detects ref type and composes multiple data sources, which is useful beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no redundancy. First sentence states purpose and scope, second adds functionality and usage guidance. Perfectly front-loaded and efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description gives a high-level summary of returned data (issue, linked commits, traces). Sufficient for understanding the tool's output. Could be more detailed but adequate for a read-only tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description mentions auto-detection for ref and linked commits for maxLinkedCommits, but adds minimal new meaning beyond what schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it provides unified context for issue/PR/commit/error refs and composes issue + linked commits + related traces. Distinguishes from sibling tools by recommending preference over raw gh/git tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Prefer over raw gh / git tools' giving clear guidance when to use this aggregated tool over more specific siblings. Does not mention when not to use, but this is acceptable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true. The description adds value by specifying that the tool queries across multiple source types and provides answers, which goes beyond the annotation's safety profile. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler. The core purpose is front-loaded, and every word contributes to describing the tool's function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema is present, and while the description hints at returning answers, it does not describe the response structure or behavior like pagination. Given the detailed input schema, this gap makes it only partially complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all parameters. The description summarizes three filter types (traceType, time window, natural key) but does not add substantive meaning beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses specific verbs like 'query' and 'filter', and names the exact resources (approval, enrichment, recipe-run trails). It distinguishes from siblings like ctxSaveTrace by framing it as a query operation that answers 'why did X happen'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implicitly guides usage by stating it is a 'unified query' over trace types, but does not explicitly contrast with alternatives like ctxSaveTrace or other query tools. The context is clear, but no exclusions are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations (readOnlyHint false, destructiveHint false) are consistent. Description adds behavioral constraints like keeping problem and solution to one line each, and explains persistence and visibility across sessions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states purpose and effect, second adds usage constraint and future availability. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple write tool with 4 params and no output schema, description covers what, when, how (one line each), and where results are visible. Complete and sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all 4 parameters. Description reinforces constraints like one line for problem/solution and max 10 tags, adding clarity without redundancy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Record a problem+solution trace after resolving a task' with a specific verb and resource. It distinguishes from sibling ctxQueryTraces by focusing on recording rather than querying.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use ('after resolving a task') and mentions future retrieval via ctxQueryTraces and session-start digest. Does not explicitly state when not to use, but context is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations mark it as destructive, and the description adds that it uses VS Code's trash when connected with a native fs fallback. However, it does not disclose other behaviors like permission needs or effects on open files.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no extraneous words. The action and key behavior are front-loaded, making it efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple deletion tool with three parameters and no output schema, the description covers the core behavior and the trash fallback, which is important for understanding side effects. It lacks return value info but that is acceptable without output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage for all three parameters, so the description adds no extra meaning beyond the schema descriptions. The mention of 'recursive' and 'useTrash' aligns with schema but does not enrich it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool deletes files or directories, specifying both workspace and absolute paths. It distinguishes from siblings like renameFile or createFile by focusing solely on deletion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. No prerequisites (e.g., file existence) or conditions (e.g., file not open) are mentioned, leaving the agent to infer context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark destructiveHint=true; description adds 'from workspace root' for scope. No mention of irreversibility or side effects beyond what annotations imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with no unnecessary words, front-loaded with action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Low complexity tool with 1 param and no output schema. Description is sufficient but could clarify what constitutes a 'plan file' beyond the schema example.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage with description and example. Description adds no extra semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the verb (Delete), resource (plan file), and location (workspace root). Distinguishes from siblings like deleteFile, createPlan, updatePlan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use vs alternatives (e.g., deleteFile, updatePlan). Does not mention prerequisites such as file existence or impact on active plans.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations set readOnlyHint=true, indicating no destructive side effects. The description adds that it uses tsc or ts-prune, which suggests it may be slower or require a project setup, but does not elaborate on other behavioral traits like file access, performance impact, or output format. With annotations covering safety, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, efficient sentence that conveys the essential information without waste. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with well-documented parameters and no output schema, the description covers the purpose and method. It lacks details on the return format or limitations, but given the tool's simplicity and the presence of readOnlyHint, it is largely complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description does not add new meaning beyond the schema. The description mentions the purpose but not the parameters. The schema already documents includePatterns (reserved) and maxResults. The description's contribution is minimal, so baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Find' and the resource 'unused exports, locals, parameters', specifying the mechanism (tsc --noUnusedLocals or ts-prune). This is specific and distinguishes it from sibling tools like findReferences or findImplementations, which search for used references.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool vs alternatives such as findReferences or diagnostic tools. The description does not mention exclusions, prerequisites, or scenarios where it should not be used.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide destructiveHint: true, alerting that the tool has destructive effects. The description adds clarity by specifying the identification method but does not disclose additional behavioral traits like terminal process termination or state loss. Given annotations, the description adds moderate value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no extraneous words. Every part serves a purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 2 optional parameters and no output schema, the description is mostly complete. It could be improved by noting that at least one identifier is required or that the action is irreversible, but it covers the essential operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% description coverage for both parameters. The description reiterates 'by name or index' but does not add significant new meaning beyond the schema. According to guidelines, baseline is 3 when coverage is high.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Close' and the resource 'VS Code terminal by name or index', making the tool's purpose unambiguous. It effectively communicates what the tool does without relying on the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like createTerminal or listTerminals. It does not mention prerequisites (e.g., needing to list terminals first) or specify that at least one of name or index must be provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark destructiveHint=true, so mutation is clear. The description adds that edits are atomic and uses VS Code or native fs, which informs about execution context. However, it does not disclose what happens on failure, file permissions, or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the most critical information (insert/delete/replace, 1-based, atomic). Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should clarify what the tool returns (e.g., success/failure, updated content). It provides workspace-only constraint but lacks return value details and error scenarios. Sufficient for a simple mutation tool but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already describes each parameter. The description adds the context of 1-based positions and atomicity but does not add meaning beyond the schema for individual parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (insert/delete/replace), the resource (text in files), and the constraints (1-based line/col, atomic multi-edit, workspace files only). It distinguishes from siblings like 'replaceBlock' or 'searchAndReplace' by specifying atomic multi-editing and line/column positioning.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for editing text files with line/col precision but does not explicitly state when to use this tool versus alternatives like 'replaceBlock' or 'stageEdit'. No guidance on when-not-to-use or prerequisites is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, and the description adds that missing issues are flagged as unresolved (not errors), which is beyond annotations. It does not detail idempotency or all side-effects, but it is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (two sentences) and front-loaded with the verb 'Enrich'. Every sentence adds value with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description adequately explains the parsing and classification behavior. However, it does not specify the output format, leaving some ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully describes the 'ref' parameter (defaults to HEAD, passed to git show). The description adds no new parameter-level details, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it enriches a commit with linked issues by parsing #N/GH-N refs, fetching issue state, and classifying. It distinguishes from siblings like fetchGithubIssue or getCommitDetails.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what the tool does but does not explicitly state when to use it versus alternatives. While sibling tool names provide context, the description itself lacks usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so safety is clear. Description adds behavioral context: parses traces, filters to in-workspace files, returns commit info. Discloses no destructive side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that front-loads the main action, followed by supported trace formats and output summary. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description explains return structure (per-frame commit + top suspect). Sufficient for a tool with clear input schema and read-only annotation. Could mention error handling or performance bounds.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers both parameters with descriptions (100% coverage). Description adds little beyond schema, only hinting that stackTrace is multi-line and maxFrames defaults to 10 (already in schema).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the verb 'map', resource 'stack-trace frames to introducing commits', and scope 'via git blame'. Distinguishes from sibling tools like gitBlame and enrichCommit by specifying parsing Node/Python/browser traces and returning per-frame commit plus suspect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage for debugging stack traces, but no explicit when-to-use or when-not-to-use. Doesn't mention alternatives like gitBlame or testTraceToSource, which could be more appropriate for simpler blame queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, indicating safe read operation. The description adds critical behavioral context: 'Session must be paused at a breakpoint'. This goes beyond annotations and informs the agent of a prerequisite, avoiding errors.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences: first states action, second states prerequisite. No unnecessary words. Every sentence adds value. Ideal for quick consumption by an LLM.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete in terms of usage condition but does not mention the return value or error handling (no output schema available). While the tool name implies evaluation yields a result, explicitly stating the output could improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 3 parameters with full descriptions (100% coverage). The tool description does not add extra meaning beyond what the schema provides. Baseline 3 is appropriate since schema already handles parameter explanation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it evaluates an expression in an active debug session, specifying the verb and resource. It distinguishes from siblings like startDebugging or getDebugState by specifying the prerequisite (paused at breakpoint).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states the condition for use: debug session must be paused. It implies when to use (during active breakpoint pause) but does not explicitly mention when not to use or alternatives. However, the context is clear and no sibling tool duplicates this exact function.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does not disclose any behavioral traits such as side effects, required permissions, or behavior on invalid commands. For a generic command executor, this lack of information is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences, front-loading the purpose and providing a key usage tip. Every sentence earns its place with no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's generic nature and lack of output schema, the description is notably incomplete. It omits details on return values, error handling, and the variable nature of arguments, which are important for an AI agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents both parameters well. The description adds value by referencing listVSCodeCommands for discovering command IDs, providing practical guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (execute) and resource (VS Code command by ID), and provides a method to discover valid IDs via listVSCodeCommands, effectively distinguishing it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description advises to use listVSCodeCommands to discover IDs, which provides a clear prerequisite. However, it does not explicitly state when to use this tool versus alternatives, but the advice serves as implicit guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds valuable behavioral context beyond the readOnlyHint annotation, specifying that it includes ±10 lines of code context, go-to-definition, and up to 5 callers. This clarifies the extent of information returned without contradicting the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that conveys all essential information without wasted words. Every element (bundle, code context, go-to-definition, callers) is clearly stated and earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Without an output schema, the description adequately explains the return value (diagnostic details, code context, go-to-definition, callers). It covers the essential aspects for a moderately complex tool, though it could benefit from mentioning whether the diagnostics are from all sources or only linting/errors.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for all three parameters. The description mentions 'file/line/character position' but does not significantly enhance the schema's meaning. The addition of 'code context' and other bundled items is more about output than parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool bundles diagnostic details, code context, go-to-definition, and callers for a specific file/line/character position. It uses a specific verb 'Bundle' and resource 'diagnostic details + code context + go-to-definition + callers', distinguishing it from similar siblings like 'explainSymbol' or 'getHover'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for file/line/character positions but does not explicitly state when to use this tool versus alternatives. No exclusions or sibling comparisons are provided, leaving the AI agent to infer the context from the description and sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description fully discloses what the tool returns and the optional boolean parameters that enhance output, including a prerequisite for useMemoryGraph. This goes beyond the readOnlyHint annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, well-structured sentence that efficiently conveys the tool's purpose and capabilities without extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers key return values and optional flags, but without an output schema, it could be more explicit about the response format or structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds context by listing the returned data types and noting the memory graph prerequisite, adding value beyond parameter descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool aggregates multiple symbol details (type signature, docs, definition location, call hierarchy, reference count) into one call, distinguishing it from sibling tools that return only one aspect.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use when comprehensive symbol info is needed, but it does not explicitly state when not to use it or provide alternatives for partial info.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description's 'Fetch' aligns. The description adds the connector requirement and the time scope, but does not elaborate on error behavior if the connector is missing or on pagination limits. It meets the baseline but lacks extra context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two sentences, each conveying essential information (fetching events, time range, prerequisite). No extraneous words, and the most important action is front-loaded. It is an model of conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description briefly mentions return type ('Returns events' ) but omits details like structure (e.g., summary, start, end). However, the tool's purpose is simple, the parameters are well-defined, and an AI agent can infer the likely output format. Minor gap, but overall sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides full descriptions for all three parameters (daysAhead, maxResults, calendarId). The description only reiterates 'next N days' which matches daysAhead, adding no new meaning. Schema coverage is 100%, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Fetch' and the resource 'upcoming Google Calendar events'. It specifies the scope (next N days) and a prerequisite (Google Calendar connector connected). There are no sibling tools with similar purpose, so it is well-distinguished.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly mentions a prerequisite (connector required) and implies the tool is for upcoming events. However, it does not provide guidance on when not to use this tool (e.g., for past events or other calendars) or mention alternatives, which is a minor gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true. The description adds beyond annotations by specifying the return fields (title, body, state, labels, assignees, author) and the connector requirement. No contradictions. However, it does not mention error behavior or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with the action, then lists return values and a prerequisite. No redundant information or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description covers the return fields and a key prerequisite. It could mention error handling or limitations, but is sufficient for a simple fetch operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides a detailed description of the sole parameter issueRef, so the description's statement about 'by URL or owner/repo#number ref' adds minimal additional value. With 100% schema coverage, the baseline is 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it fetches a GitHub issue, specifying two identification methods (URL or short ref). It is distinct from sibling tools like fetchGithubPR (which fetches pull requests), making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the prerequisite of having a GitHub connector connected, but does not explicitly state when to use this tool versus alternatives (e.g., fetchGithubPR for pull requests). The context is clear, but exclusions are implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, and description consistently describes a read operation. Adds value by listing returned fields and connector requirement. No contradictions; could mention error handling or pagination but not required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two efficient sentences: first covers purpose and output, second covers a key prerequisite. No filler, front-loaded, easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one param and no output schema, description covers main usage and result. Could mention error cases, but overall sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear param description. Tool description repeats the same info without adding new meaning. Baseline 3 appropriate since schema already documents the param.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly specifies verb 'Fetch', resource 'GitHub pull request', and lists returned fields (title, body, state, etc.). Distinguishes from siblings like fetchGithubIssue by focusing on PR-specific data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States prerequisite ('Requires GitHub connector connected'), implying when to use. Does not explicitly exclude alternatives or provide when-not guidance, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true. The description adds the list of returned fields, providing useful context about what data the agent can expect. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences: one stating the action and one listing returns and prerequisites. Every word is informative with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description covers key return fields and a prerequisite. It lacks error handling details (e.g., invalid issue ID), but for a simple read-only tool this is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with a clear description of the issueId parameter (identifier or URL). The description adds no additional parameter information beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches a Linear issue by identifier or URL, and lists the returned fields (title, description, state, assignee, labels, priority). It distinguishes from siblings like createLinearIssue and updateLinearIssue by being a read-only fetch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the prerequisite 'Requires Linear connector connected.' It does not explicitly state when not to use this tool or direct to alternatives, but the context of siblings implies this is for fetching, not mutating.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, and the description aligns by describing a fetch operation. It further explains the enrichment process and return value, which adds behavioral context beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences: the first states purpose and return value, the second states the prerequisite. No redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description adequately covers the tool's purpose, return value, and prerequisite. With no output schema, it correctly describes the output. The input schema fully documents parameters. The tool is simple and well-covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters are fully described in the input schema (100% coverage). The description adds little that is not already in the schema, but it does relate maxFrames to the enrichment process. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches a Sentry issue and enriches its stack trace with git blame, returning per-frame commit attribution and top suspect commit. This distinguishes it from sibling tools like fetchGithubIssue or fetchLinearIssue.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the prerequisite that a Sentry connector must be connected, which guides usage. However, it does not explicitly state when to use this tool over alternatives or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotation readOnlyHint=true already indicates safe read. Description adds value by specifying exact returned fields. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with action and output, no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, description clearly lists the three returned fields. Sufficient for a simple getter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters in schema (100% coverage). Description adds no parameter info, but none needed. Baseline 4 due to no params.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb 'Get' with specific resources (workspace name, team ID, bot user ID). Distinguishes from sibling Slack tools like slackPostMessage and slackListChannels.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Use to confirm Slack is connected' which guides when to invoke it. No explicit alternatives or exclusions, but contextually clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true. The description adds the behavioral trait of respecting .gitignore, which is useful beyond annotations. However, no other traits like recursion depth, performance, or whether it returns relative/absolute paths are disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first states the main purpose, second adds the gitignore behavior. No unnecessary words, front-loaded, efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple file-finding tool with two parameters and no output schema, the description is adequate but lacks details about return format (e.g., list of paths) and limits. The agent can infer success but may need additional context for full usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. The description repeats the pattern concept but adds no additional meaning beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds files by name or glob pattern, which is distinct from sibling tools like searchWorkspace (content search) or findReferences (symbol references). The verb 'Find' and resource 'files' are specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for file-finding tasks and notes .gitignore respect, but does not explicitly contrast with alternatives or provide when-not-to-use guidance. Usage context is implied but not fully explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the tool is read-only. The description adds no additional behavioral traits beyond the schema. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with no unnecessary words. Front-loaded with the core purpose. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple code navigation tool with no output schema, the description is mostly complete. However, it could mention the return format (e.g., locations) for full clarity, but not required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All 3 parameters are fully described in the input schema (100% coverage). The description adds no extra meaning; baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool finds implementations of interface, abstract method, or abstract class. It uses a specific verb ('Find') and resource types, distinguishing it from siblings like 'findReferences' and 'goToDefinition'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'batchFindImplementations' or 'findReferences'. The description provides no context for selection or exclusion.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint: true, meaning read-only. The description adds that it uses VS Code LSP, which implies potential blocking behavior but does not detail any additional traits like rate limits or state side effects. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that conveys the essential purpose concisely. It is front-loaded with key information and contains no unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple, and the schema covers parameters well, but no output schema is provided. The description could mention the return format (e.g., list of reference locations) or explain how the cursor parameter enables pagination. Currently, it is adequate but leaves some missing context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with detailed descriptions for all four parameters (filePath, line, column, cursor). The tool description adds no extra meaning beyond what the schema already provides, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (Find), the resource (all references to a symbol at a given position), and the mechanism (using VS Code LSP). It distinguishes itself from sibling tools like findImplementations (finds implementations) and findFiles (finds files).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like findImplementations or batchFindImplementations. It does not mention when not to use it or any prerequisites, leaving the agent to infer usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, and description adds details about search method and optional coverage. No contradictions. Good disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded, no redundant information. Highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description implies list of test files. Could mention return format for completeness, but adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers both parameters fully (100%). Description does not add meaning beyond schema, baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb 'find', resource 'test files', and method 'import search + name patterns'. Distinguishes from siblings like generateTests or runTests.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage to locate test files, but no explicit when-to-use or alternatives. Optional coverage parameter is noted.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses behavior: uses VS Code source.fixAll when connected, falls back to linters. Annotations confirm destructive and idempotent. Description adds value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with purpose. No unnecessary words. Efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given simple tool with one param, thorough schema coverage, clear annotations, and no output schema, description provides sufficient context including fallback behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Single parameter filePath is fully described in schema (100% coverage). Description does not add extra meaning, but baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it auto-fixes lint errors, names specific VS Code command (source.fixAll) and fallback linters (eslint/biome/ruff), distinguishing from sibling tools like applyCodeAction or formatDocument.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage context: connected to VS Code uses source.fixAll, otherwise falls back to linters. No explicit when-not or alternatives, but clear enough for typical use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description adds limited value by listing return fields and examples. No additional behavioral details (e.g., performance, limitations) are provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with clear purpose and return format. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately describes the return value format and examples. For a simple read tool, this is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description does not add extra meaning beyond the schema's filePath description. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it returns foldable regions (functions, classes, imports, comments) with {startLine, endLine, kind}. Differentiates from generic getDocumentSymbols by focusing on foldable regions, but does not explicitly distinguish from siblings like selectionRanges.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as getDocumentSymbols or findImplementations. Does not mention when not to use it or provide context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (destructive, idempotent), the description adds that formatter errors propagate and save is skipped on format failure, which is useful behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences front-load the main action and error handling, with no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, the description plus annotations cover the needed context well.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage describing 'filePath'. The description does not add extra parameter details beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool formats and saves a file in one call, distinguishing it from the sibling tools 'formatDocument' and 'saveDocument'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use (combining two steps) and distinguishes from siblings, but doesn't explicitly state when not to use or provide alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint and idempotentHint. The description adds minimal behavioral context (e.g., fallback CLI tools), but does not detail whether it modifies the file in-memory or on disk, or other side effects. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no wasted words. Front-loaded with the core action. Efficient and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with 1 parameter, no output schema, and clear annotations, the description is adequate. It could mention that it formats the entire file or that it uses project config, but overall it provides enough context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% coverage for the single parameter filePath, and the description does not add semantic meaning beyond the schema's description. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Format' and the resource 'file', and mentions specific CLI formatters. It distinguishes from sibling tools like formatAndSave (which saves) and formatRange (range formatting) by specifying it uses VS Code formatter or CLI fallback for the entire file.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for formatting files but provides no explicit guidance on when to prefer this over siblings like formatAndSave or formatRange. No when-not or alternative tools are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description does not add significant behavioral transparency beyond the annotation readOnlyHint=false. It mentions 'via LSP formatter' which implies standard behavior, but lacks details on side effects, undo capability, or error states.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the purpose and includes a performance comparison. No wasted words, making it highly efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core functionality but lacks details on return values, error conditions, or prerequisites (e.g., file must be open, LSP active). Given the simplicity of the tool, it is minimally adequate but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Since the input schema has 100% description coverage for each parameter, the description does not add new meaning. It provides minimal extra context beyond the schema, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it formats a line range using LSP formatter, with a specific verb and resource. It distinguishes itself from the sibling tool formatDocument by highlighting it is faster for large files, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides guidance on when to use this tool ('for large files' to be faster than full formatDocument), implying a choice between range vs full formatting. However, it does not explicitly list alternatives or exclusions beyond the comparison with formatDocument.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, and the description confirms it extracts symbol types without mutation, adding context about JSDoc extraction. No contradictions, but could elaborate on JSDoc handling and import traversal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, 12 words, front-loaded with the core purpose. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters fully described in schema and no output schema, the description provides sufficient context about purpose and extracted symbols. Missing explicit output format details (though implied by 'markdown/JSON').

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema covers 100% of parameters with descriptions. The description adds minimal extra context (e.g., TS/JS focus) but does not significantly enhance understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it generates API docs in markdown/JSON for TS/JS exported symbols, extracting functions, classes, interfaces, and JSDoc. This distinguishes it from sibling tools like generateTests, getHover, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it (when API documentation is needed) but does not explicitly state when not to use it or mention alternative tools like getHover for individual symbol documentation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

While readOnlyHint already indicates a read-only operation, the description adds that the tool returns describe/it content (test scaffold) and explicitly states it does not write files, providing additional behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two sentences, immediately stating the tool's purpose and a key behavioral note, with zero wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no output schema and a readOnly annotation, the description sufficiently covers the purpose, output type, and file-writing constraint. It lacks details on error handling or limitations, but these are minor for this simple generation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides full descriptions for all three parameters (100% coverage). The top-level description adds the nuance that the tool works on files with exported functions/classes, but this only marginally enhances parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool generates test scaffolding from exported functions/classes, and explicitly notes it returns content without writing files, distinguishing it from sibling tools like runTests or findRelatedTests.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for generating test content from exported code and states it does not write files, but lacks explicit guidance on when to use versus alternative test-related tools (e.g., runTests, findRelatedTests).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true. The description reinforces this with 'Query' and adds specific behavioral details about what the log includes (timing, status, percentiles, co-occurrence), providing context beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently conveys the tool's function without any extraneous words. It includes key aspects of the log query without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the description covers the main purpose and some output details, it lacks information about the return format or potential pagination. Given the absence of an output schema, a bit more detail on the structure of results would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all parameters are already well-documented in the JSON schema. The description does not add any additional parameter semantics beyond summarizing the output, which is sufficient given the schema's richness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it queries the tool call log, specifying details like names, timing, status, percentiles, and co-occurrence. It distinguishes this tool from sibling tools that deal with other logs (e.g., getGitLog, getBufferContent).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use guidance is given. The description only states what the tool does, leaving the agent to infer usage context from the tool name and siblings. No alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, so the description does not need to restate that. The description adds what data the report contains, which is useful. However, it does not disclose any limitations, rate limits, or data freshness, which are not critical for a read-only report tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence that directly states the content of the report. No unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one optional parameter, but there is no output schema. The description gives a high-level idea of return data (top tools, hook events, automation tasks) but lacks detail on structure (e.g., is it a list, object, any nested fields). Given the simplicity, it is marginally adequate but could be improved.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description does not mention the windowHours parameter or add any meaning beyond the schema. The schema itself provides a clear description and constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the report contents: 'top tools by call count, hook events, recent automation tasks.' It implies the tool retrieves a session analytics report. However, it does not explicitly use a verb like 'retrieves' or 'gets', relying on the tool name for action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like getSessionUsage or getPerformanceReport. No context about prerequisites or when not to use it is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, and the description confirms a read operation (architectural overview). It adds value by stating the return type ('structured query plan') and the prerequisite (codebase-memory connected). No contradictions; behavior is adequately disclosed beyond structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no fluff. The first sentence captures purpose and scope, the second adds prerequisites and return information. Front-loaded and every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and high schema coverage, the description covers purpose, return type ('structured query plan'), and a key prerequisite. The 'structured query plan' could be more specific, but the overall context is sufficient for a simple read tool with two parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema coverage is 100% with clear descriptions for both parameters ('aspects' and 'maxNodes'). The description does not add significant meaning beyond the schema, only mentioning the return type. Baseline 3 is appropriate since schema already provides full parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides an 'architectural overview via codebase-memory graph' with specific aspects (module boundaries, dependencies, ADRs, hotspot files). This verb-resource pair is distinct from sibling tools like getDependencyTree or getProjectContext, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions the prerequisite 'Requires codebase-memory connected' but does not explicitly guide when to use this tool versus alternatives (e.g., getDependencyTree, getProjectContext). There is no when-not-to-use or alternative naming, so usage guidance is only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true. Description adds specific status categories beyond annotations, but does not elaborate on behavioral traits like refresh frequency or error states.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no redundant words, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and no output schema, the description covers the main status aspects. Could mention read-only nature but annotations already do.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, and schema coverage is 100%. Baseline of 4 applies since description adds no parameter info but none is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States it provides IDE bridge status including ext connection, circuit breaker, uptime, and tool availability. Clear purpose but does not explicitly differentiate from sibling tools like getConnectorStatus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives, no exclusions or context provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond the readOnlyHint annotation by detailing that unsaved changes are included and that the tool is limited to workspace files. It accurately communicates the tool's behavior without contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with only two sentences, front-loading the core functionality. Every sentence serves a purpose: stating what it does, when to use it, and what it returns.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with no output schema, the description covers the main functionality and key behavior (unsaved changes). However, it does not clarify behavior when the file is not in the buffer (e.g., whether it reads from disk). This minor gap prevents a perfect score.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% coverage with descriptions for all parameters. The description does not add further clarification or examples, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads a workspace file from the VS Code buffer including unsaved changes, with a specific verb and resource. It also mentions returning an isDirty flag and restricts to workspace files, distinguishing it from sibling tools like editText or getOpenEditors.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly advises to use this tool before editText, providing clear contextual guidance. While it does not list exclusions or alternatives, the instruction is sufficient for typical usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true; description does not contradict and adds the direction behavior. No additional disclosure (e.g., performance, auth) beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, no redundancy. Every sentence serves a clear role.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, yet description omits return value explanation. Also does not mention cursor usage despite it being a key parameter. Incomplete for a 6-param tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. Description adds minimal value by explaining the direction enum, but other parameters are already well-described in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool gets the call hierarchy for a function/method, with specific verb and resource. However, it does not differentiate from sibling tools like getTypeHierarchy or findReferences.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides guidance on using the direction parameter for incoming/outgoing/both, but lacks explicit when-not-to-use or alternative recommendations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the tool is a safe read operation. Description adds that it returns diagnostics and reference counts, but does not disclose potential performance implications, limits, or whether it triggers analysis. With annotations covering safety, a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence of 10 words, highly concise. Every word earns its place, starting with the key concept 'Blast radius' for immediate understanding. No unnecessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description lacks detail on output format (e.g., structure of diagnostics, counts) and does not explain how to interpret 'blast radius'. With no output schema, the description should provide more context. Also, given many similar sibling tools, it does not help the agent decide when to invoke this over others.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% description coverage for all three parameters. The description adds no further meaning beyond the schema, e.g., it does not explain how 'changedSymbols' relate to the output. Baseline 3 is correct when schema is sufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool computes 'blast radius' after editing a file, providing diagnostics and reference counts for changed symbols. It uses specific verbs and resources, making the purpose clear, though it does not explicitly differentiate from similar sibling tools like findReferences or getDependencyTree.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., findReferences, getDependencyTree). Missing context such as prerequisites (file must be saved?) or after-edit timing. Agent must infer usage from description alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation 'readOnlyHint: true' already indicates no side effects. The description ('Get') aligns but adds no further behavioral context (e.g., polling behavior, rate limits). Baseline score with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-formed sentence with 12 words. No filler; every word is necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only status check with one parameter and clear annotations, the description is sufficient. There is no output schema, but the description hints at the return content ('status and output'), which is reasonable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the schema description for taskId is adequate. The description does not add any additional parameter meaning beyond what is already in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get'), the resource ('status and output of a Claude task'), and the relationship to 'runClaudeTask', which distinguishes it from sibling tools like cancelClaudeTask or listClaudeTasks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is used after runClaudeTask to check progress, but no explicit when-not-to-use or alternative guidance is provided. However, the context is clear enough for an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description aligns with the readOnlyHint annotation (true) by describing a read operation. However, it adds no additional behavioral context beyond what annotations provide (e.g., no mention of side effects or analysis triggers). No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One concise sentence (13 words) that clearly states the purpose with no unnecessary words or repetition. Excellent front-loading.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 required params, no output schema, and a simple read operation. The description is sufficient for the agent to understand the basic purpose, though it does not specify the return format (e.g., list of action names). Given the simplicity, this is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for all 5 parameters. The description only mentions 'range in a file', which does not add meaning beyond the schema descriptions (e.g., line/column numbers). Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the verb 'Get', the resource 'code actions', and the scope 'for a range in a file'. It clearly distinguishes from siblings like applyCodeAction (which applies the action) and previewCodeAction (which previews).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide guidance on when to use this tool versus alternatives (e.g., applyCodeAction, previewCodeAction). The context is implied but no explicit when-to or when-not-to guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.