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

The description discloses that the tool writes/regenerates the index, and importantly explains the read-only CI behavior ('fails instead of writing on drift'). This complements the readOnlyHint: false annotation by giving concrete failure semantics, though it does not detail side effects or required permissions.

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 action and resource, then usage timing, then the parameter mode. Every sentence earns its place with no filler 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?

For a simple one-parameter write tool with no output schema, the description fully covers what the tool does, when to use it, and how the parameter changes behavior. The inclusion of failure mode in CI makes it operationally 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?

The input schema already fully describes the 'check' parameter with high coverage, and the description adds practical context by explaining the CI-mode behavior. This reinforces the schema without redundancy, raising it above 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 opens with a specific verb ('Regenerate') and a clear resource ('CAPABILITIES.yaml'), identifying it as the package's coverage index. This distinguishes it from sibling tools like list_skills or list_rules, which query rather than update the index.

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 after adding or removing an artifact to keep the index current,' which is clear guidance for when to invoke it. It also explains the CI-mode use case with 'check: true', but does not name alternative tools to use instead of this one, such as list_* commands.

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?

With only readOnlyHint: false, annotations are minimal. The description fully discloses the write behavior, filesystem target, return value ('returns the written entry plus its resolved target path'), safety validation ('path outside the allowlist... raises an error before writing'), and the dry_run side-effect-free preview. This goes well beyond what annotations provide.

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 four sentences, front-loaded with the primary action, then usage context, then safety/behavior specifics. Every sentence adds critical information: what it does, when to use it, the write behavior and safety, and the dry_run escape hatch. 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 6-parameter write tool with no output schema and minimal annotations, this description is remarkably complete. It covers the target file locations, the return payload, path restrictions, dry_run behavior, and downstream consumers. An agent can confidently select and invoke this tool without further clarification.

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. The description adds meaningful behavioral semantics for the 'path' parameter (allowlist and traversal checks) and clarifies dry_run's purpose. It also explains the entry body ('text') in the context of a JSONL log, enhancing understanding beyond the schema's bare field 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's purpose: 'Append one structured entry to the consumer project's chat-history log (a JSONL file).' This is a specific verb+resource that distinguishes it from siblings like chat_history_read, which retrieves the log, and other memory tools that operate on different stores.

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 to record a decision, note, or phase marker that should persist into a later session or be distilled by `mine_session`.' This gives clear context for when to use the tool. It also notes back-compat paths and the dry_run option, but it does not explicitly state when not to use it (e.g., for ephemeral or non-history data), so it falls short of a 5.

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, it adds valuable context: returns the resolved file path plus matching entries (newest last), describes path resolution with back-compat, warns that rotation invalidates refs, and notes that history entries are large so 'index' mode is helpful. These details give the agent a clear behavioral model.

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 at four sentences, each serving a distinct purpose: what it reads, when to use it, return shape, and filter guidance. No redundant text or filler.

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 8 optional parameters and no output schema, the description covers the core aspects: purpose, file location, filtering hints, and return format. It lacks explicit mention of error conditions or edge cases, but the schema and rich parameter descriptions fill the gap reasonably.

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 baseline is 3. The description adds a useful tip about combining 'session', 'last', and 'entry_type' filters, but it doesn't further explain each parameter or add semantics beyond what the 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?

The description uses the specific verb 'Read' with a concrete resource ('chat-history JSONL') and gives exact paths, making the tool's function unambiguous. It differentiates from sibling 'chat_history_append' by emphasizing read-only access and mentions return contents (entries, resolved path).

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 states the intended use case: recovering context from earlier sessions at the start of a new task. It also advises combining filters to narrow results, but it doesn't explicitly mention when not to use it or name alternative tools (e.g., memory_get) for different context sources.

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 include readOnlyHint=true, and the description reiterates 'Read-only,' with no contradiction. It adds behavioral detail by naming the commands executed and stating that results are returned per check, going beyond the annotation's simple safety flag.

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 action, command details, and output type, then a clear usage recommendation. Every word earns its place 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 no-parameter tool with no output schema, the description adequately covers the operation, return semantics (pass/fail per check), and when to use it. There are no essential 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?

The input schema has zero parameters, so schema coverage is trivially 100%. No parameter information is needed, and the baseline for zero-parameter tools is 4.

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 a specific verb+resource combination ('Run the consumer conformance contract') and clearly identifies the underlying command (`doctor --ci` plus installed-and-firing checks) and output (pass/fail per check). It distinguishes this from sibling tools like `doctor_report` or `run_tests` by emphasizing verification of a consumer project's install wiring.

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 an explicit usage scenario: 'Use to verify a consumer project's install is fully wired before relying on it.' It does not mention when not to use the tool or alternatives, but the context is clear and actionable.

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 already marks it as read-only, and the description adds meaningful behavioral context beyond that: 'no network call, no billing' and 'without spending'. This clarifies the side-effect-free nature in a way the annotation alone does not convey. 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?

The description is only two sentences and packs in purpose, safety, and timing without any filler. It is front-loaded with the action verb and resource, making it immediately understandable.

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 simple read-only nature and the rich annotations and schema, the description adequately covers purpose, usage timing, and safety. It does not describe the return format or precision of the estimate, and since there is no output schema, that is a minor gap, but not enough to lower the score further.

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 both parameters, so schema coverage is 100%, giving a baseline of 3. The description adds value by specifying that the input can be a 'roadmap, diff, prompt, or file set', which expands on the schema's narrower 'roadmap, diff, or file' phrasing. Depth is not mentioned, but the schema's enum covers it sufficiently.

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 specific action ('Estimate the token cost') and the resource ('AI-council debate over a given input'). It also distinguishes itself from a real council run by emphasizing 'without spending — no network call, no billing', leaving no ambiguity about its purpose.

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 phrase 'Use before deciding whether to authorize a real council run' explicitly defines when to use this tool. While it provides a clear context, it does not explicitly mention when not to use it or name an alternative tool, so it stops short of a full 5.

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 declares the tool is read-only, and the description reinforces this with 'Read-only.' Beyond that, it adds useful behavioral context about the nature of the diagnostic (checks for drift, hook wiring, settings schema, freshness) and the structured form of the output, which is not fully derivable from the annotation 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?

The description is two sentences, front-loaded with the action and resource, and contains zero filler or redundant content aside from the harmless repetition of 'Read-only.' Every clause adds information about the tool's purpose, output, or 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?

For a zero-parameter, read-only diagnostic tool with no output schema, the description provides all necessary context: what it runs, what the report covers, why you would use it, and its safety profile. The annotations and schema further support completeness, leaving no significant gaps for an agent to invoke it 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?

The tool has zero parameters, so the baseline of 4 applies per the rubric. The schema is fully covered (100%) and the description does not need to clarify any parameter details because none exist. The description appropriately focuses on behavior and use case.

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 a specific verb ('Run') and names a precise resource ('consumer-project doctor diagnostic'), while detailing the report's contents (install drift, hook wiring, settings schema, discovery manifest freshness). This clearly distinguishes it from siblings like run_tests or telemetry_report by identifying a unique diagnostic target and purpose.

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 when to use the tool: 'Use to triage a misbehaving install.' This provides clear context for the appropriate use case. However, it does not mention when not to use it or suggest alternatives among the sibling tools, so it stops short of a full 5.

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 explicitly states the tool is read-only, never writes files, never spawns git, and details the exact return payload structure (summary and per-file results). This adds meaningful behavioral context well beyond what annotations provide.

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 and well-structured, front-loading the primary purpose, then usage guidance, then safety/behavior, then return format, and finally parameter usage. Every sentence contributes valuable information with no redundancy or filler.

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 purpose, when to use, safety/read-only behavior, return payload, and parameter semantics. With a simple one-parameter input schema and no output schema, the description provides all necessary context for an agent to select and invoke 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?

The schema already provides a thorough description for the 'paths' parameter, including the meaning of empty/missing values (full tree scan). The description merely restates this ('Pass 'paths' to lint a subset; omit for a full tree scan') without adding new information. Schema coverage is 100%, so a 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 uses a specific verb (lint) and a clear resource (skill, rule, command, guideline, and persona markdown files) to state what the tool does. It distinguishes itself from siblings by being the only linting tool among the listed tools, and it mentions 'frontmatter and structural errors' as the focus.

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 explicit context for when to use the tool ('Use before committing or opening a PR that adds or edits any of those artifacts'), which is strong guidance. It does not explicitly name alternatives or say when not to use it, but the sibling tools are clearly unrelated in function, so the omission is minor.

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 meaningful behavioral detail beyond the readOnlyHint annotation: it labels itself a 'Read-only manifest view,' states it takes no arguments, and reveals the response shape ('Returns a count plus a commands array'). No contradictions 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: the first states what it does, the second gives usage context, read-only nature, argument count, and return format. Every sentence earns its place with no redundant or filler content.

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 list tool with no parameters and no output schema, the description fully covers purpose, usage context, behavior, and return structure. Sibling relationships are implied through the tool name and the usage note, so no further context is needed.

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?

There are zero parameters, and the schema coverage is 100%, so there is nothing to misinterpret. The description reinforces 'takes no arguments,' matching the empty schema. Baseline for 0 params is 4, and no further parameter explanation 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?

The description opens with a specific verb ('Enumerate') and resource ('every slash command the server currently exposes as a prompt'), and clarifies what's included ('name and description'). This clearly distinguishes it from siblings like list_rules and list_skills, which target different resources.

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 explicitly states when to use: 'Use to discover available commands before routing a user request to one.' This gives clear context. However, it does not mention alternatives or when not to use it (e.g., for rules or skills), so it lacks the explicit exclusion/alternative guidance of a top-tier score.

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 that it is a 'read-only manifest view', takes no arguments, and returns a 'count' plus 'rules' array. This offers concrete behavioral detail beyond the annotation without contradicting it.

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: the first states purpose and result structure; the second gives usage and return format. No redundant wording, front-loaded with the core action.

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-argument list tool with no output schema, the description fully covers purpose, usage, and return shape. It even notes the next step (fetch a body), making it contextually complete relative to 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, and the description explicitly states 'takes no arguments'. Since schema coverage is 100% trivially, the description adds confirmation of the empty parameter list. Baseline for zero params is 4.

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 a specific verb 'Enumerate' and identifies a distinct resource: 'behavioral rule the server exposes as a resource'. It explicitly lists what each rule includes (URI, name, description), distinguishing it from sibling tools like list_commands and list_skills.

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 provides clear usage context: 'Use to discover which rules are in effect' and explicitly names alternative tools for a follow-up action (read_resource_body or resources/read). This tells the agent when to use this tool and what to do next.

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 is reinforced by 'Read-only manifest view,' and the description adds behavioral details such as taking no arguments and returning a count plus a skills array. Since there is no output schema, explaining the return shape is valuable 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 three sentences are tightly packed: definition, usage context, and behavior/return. No waste or redundancy; each clause 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 zero-parameter read-only listing tool, the description covers what it returns, when to use it, and its read-only nature. Given the lack of output schema, the return value explanation is sufficient, and the tool's simplicity means no further context is needed.

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 tool takes zero parameters, and the input schema is an empty object. The description explicitly notes 'takes no arguments,' and with no parameters to document, the baseline of 4 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 opens with 'Enumerate every skill the server currently exposes as a prompt,' clearly identifying the action and resource. It distinguishes itself from sibling listing tools like list_commands and list_rules by focusing specifically on skills. The mention of name, description, and source further clarifies the scope.

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 explicitly states when to use: 'Use to discover which skills are available before suggesting or invoking one.' However, it does not mention when not to use or explicitly compare with alternative list tools, so it falls short of full exclusion 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?

Beyond the readOnlyHint annotation, the description discloses that unknown ids are reported per-id as 'unknown' and never cause the whole batch to fail—critical error-handling behavior that is not visible in the schema. It also reinforces the read-only nature and highlights the batching capability, adding genuine 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?

Three sentences, each earning its place: the first states the core purpose, the second gives the workflow and usage order, and the third details error behavior. There is no fluff or repetition; the description is tightly packed and front-loaded with the primary action.

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 one-parameter, read-only tool with no output schema, the description fully covers purpose, usage, error handling, and the relationship to its sibling. The 'FULL' qualifier and the per-id unknown example give enough detail for an agent to anticipate the response shape without needing a formal 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?

The input schema already describes the 'ids' parameter as 'from a detail:"index" lookup', so baseline is 3. The description adds the selection criterion ('title/tokens_estimate justify the fetch') and emphasizes the batched nature of the call, providing marginal but meaningful extra 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 opens with a specific verb-resource pair ('Batch-fetch FULL memory entries by id') and explicitly frames the tool as the 'second half of the index-first retrieval workflow', distinguishing it from sibling memory_lookup. It clearly states what the tool does and what it returns (full entries as opposed to index summaries).

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 an explicit when-to-use workflow: call memory_lookup with detail:'index' first, select ids based on title/tokens_estimate, then fetch them here in ONE batched call. It also names the alternative (memory_lookup) and the order of operations, leaving no ambiguity about 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?

The description discloses the tool's read-only nature, which aligns with the readOnlyHint annotation but goes beyond it by naming the exact data sources ('Reads `agents/memory/<type>/*.yml` plus the `agents/memory/intake/*.jsonl` signal log') and describing the return envelope ('a `status` field plus per-type `slices`'). This provides valuable context about side effects, data scope, and output structure not present in 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 front-loaded with the primary purpose, followed by usage context, workflow, data sources, and return format. Every sentence contributes value, and the 'WORKFLOW:' label provides clear structure. Despite its length, it is appropriately sized for the tool's complexity, with zero 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?

With no output schema, the description takes responsibility for explaining return values, and it does so ('Returns the v1 retrieval envelope: a `status` field plus per-type `slices` carrying the matched entries'). It also covers the `detail` modes and token_budget behavior indirectly through the schema. Considering the tool's complexity and the rich schema, the description is complete enough for an agent to use 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 description coverage is 100%, so the baseline is 3. The description adds value by explaining the strategic use of the `detail` parameter ('call with detail:"index" FIRST') and the purpose of `keys` ('anchor paths to match entries against'). While it doesn't add new meaning for every parameter, the workflow guidance enhances understanding of how to use the parameters effectively.

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 opens with a specific verb and resource: 'Retrieve engineering-memory entries for one or more memory types, optionally narrowed to specific anchor paths.' It clearly distinguishes itself from sibling tools like memory_get by explaining its role as a lookup that returns indexes and summaries, with memory_get for full bodies.

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 tells when to use the tool: 'Use before editing a security-sensitive or historically buggy file...' It also provides a step-by-step workflow ('call with detail:"index" FIRST... then fetch full bodies via memory_get') and names the alternative tool (memory_get) for fetching full entries. This is explicit guidance about when and how 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?

Annotations only say readOnlyHint=false (write operation), but the description adds that it 'Appends to the filesystem', is 'rate-limited per (type, path) within a rolling window', and 'Returns the recorded signal'. This clearly discloses side effects and constraints beyond the annotation, with 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?

The description is three focused sentences: front-loaded with the action and destination, followed by usage context, behavioral details, and return value. Every sentence adds value, with no redundancy 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?

The tool is simple with 3 required params and no output schema. The description covers purpose, target file path, append behavior, rate limiting, and return value, which is complete for an agent to decide when and how to invoke the 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% with descriptions for all three parameters (type, path, body). The description adds general context like 'short, anchored observation' and 'tied to a specific file' but does not provide additional per-parameter semantics beyond the schema. 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 uses the specific verb 'Record' with a resource ('engineering-memory signal') and a concrete destination (the monthly intake log). It distinguishes from sibling memory_lookup by stating this captures learnings so future lookups can surface them, making the tool's role clear.

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 states when to use it ('Use to capture a learning tied to a specific file') and gives examples (recurring bug pattern, ownership note). It implies the read counterpart is memory_lookup but does not explicitly exclude alternatives, which prevents a 5.

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 context: memory is entirely file-backed at a specific path, there is no external backend, and it discloses the exact return fields (status, backend, reason). This goes beyond annotation and helps the agent understand expected behavior.

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 four short sentences, each adding distinct value: purpose, backend context, read-only behavior, and return format. It is front-loaded with the purpose and contains no filler or 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 read-only status tool, the description fully covers what it does, how it behaves, and what it returns. It also explains the file-backed architecture, making the tool's behavior predictable even without an 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?

The tool has zero parameters, so the schema is trivially complete. The description reinforces this by stating 'takes no arguments', which is sufficient. No additional parameter semantics are 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?

The description starts with 'Report the memory backend status', a specific verb+resource pair that clearly distinguishes this from sibling tools like memory_get or memory_lookup which retrieve data. It unambiguously conveys that this is a status query, not a data access operation.

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 context is clear: it is a read-only status check with no arguments, and the file-backed nature is explained. However, it does not explicitly mention when not to use this tool or point to alternative siblings, leaving the user to infer distinctions from the 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 readOnlyHint annotation already declares the tool is read-only, and the description reinforces this, but more importantly it adds the return payload details ('uri', 'name', 'description', and full text body') which are not in an output schema. This provides useful behavioral context beyond the annotation, though it does not cover error cases or other edge behaviors.

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, front-loaded with the core purpose in the first sentence and usage/return details in the second. No fluff or redundancy; 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?

This is a simple single-parameter read-only tool with no output schema, and the description sufficiently covers the operation, usage condition, and return format. The sibling tools are unrelated, so no confusion. The description is complete for an agent to select and invoke 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?

The input schema fully describes the only parameter 'uri' with examples and format. The description adds minimal additional meaning (e.g., 'single resource URI' and types) but does not go beyond what the schema already provides. Given 100% schema coverage, 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 action ('Fetch the rendered body of a single resource URI'), specifies the resource types (rule, guideline, context document), and distinguishes itself from the two-step resources/list + resources/read handshake. This is a specific verb+resource definition that sets it apart 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 explicitly states when to use it ('when you already know the URI and want to inline its content into a tool-call result') and references the alternative two-step approach it avoids. This gives clear context and an explicit alternative, fulfilling the dimension perfectly.

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 goes beyond the readOnlyHint: false annotation by detailing that it mutates the git index, moves tracked files, migrates references, and regenerates the dashboard, while explicitly noting it never commits or pushes. This is valuable 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?

The description is three sentences, each earning its place: the first defines the action, the second gives usage context, and the third discloses side effects. It is front-loaded and has no 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?

The description covers the main actions and usage context. It does not mention return values or behavior when no roadmaps match, but given the absence of an output schema and the tool's mutation focus, the coverage 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?

The tool has zero parameters, so the schema provides no parameter info. The baseline is 4 for zero-parameter tools. The description adds operational semantics but does not need to explain parameters, as none exist.

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 (archive every roadmap with count_open == 0 touched on the current branch) and the resource (roadmaps). It also names the specific operations (git mv, migrate references, regenerate dashboard) and differentiates from siblings like roadmap_progress and memory_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 as the PR-gate sweep before opening a pull request,' providing a clear when-to-use context. It does not mention when not to use or explicit alternatives, but the context 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?

The description discloses that the tool writes a file inside the project tree, which is useful behavioral context beyond the readOnlyHint:false annotation. It also explains the dry_run flag to avoid writing, adding transparency about how to perform a non-destructive run. No contradictions 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 three sentences, each serving a distinct purpose: main action, usage context, and dry-run behavior. It is front-loaded with the core purpose and contains no filler or 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 the tool has one optional parameter, no output schema, and a clear write behavior, the description covers the essential aspects: what it does, when to use it, and how to avoid writing via dry_run. It could be slightly more explicit about return values, but overall it is complete 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 schema already fully documents the `dry_run` parameter with 100% coverage. The description adds minimal extra meaning by stating it 'compute counts without writing', but this largely paraphrases the schema description. Baseline 3 is appropriate since the schema does the heavy lifting.

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 regenerates `agents/roadmaps-progress.md` from checkbox states of active roadmaps. The verb 'regenerate' and specific file path make the purpose unambiguous, and it differentiates from siblings like `roadmap_archive` by focusing on syncing the dashboard 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 explicitly says to use it 'after landing roadmap work' and contrasts it with a 'shell round-trip', giving clear context on when and why to use the tool. It does not list exclusions or alternative tool names, but the guidance is sufficient 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?

Beyond the sparse annotation (readOnlyHint=false), the description reveals the compiled safety envelope: fixed argv, no shell interpolation, 120s timeout, 64KB output cap per stream. It also notes the Shell-exec pilot status and details the return fields, providing substantial behavioral context that annotations alone do not convey.

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?

Four dense sentences front-load the core action and safety constraints, then proceed to restrictions, parameter guidance, and return fields. Every sentence contributes new information with no repetition or filler.

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 two optional parameters and no output schema, the description covers purpose, safety envelope, supported/unsupported runners, parameter usage, and return value shape. The only minor omission is an explicit statement that passing neither parameter runs the full suite, but this is strongly implied by 'narrow the run.'

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?

Although the input schema already describes both parameters, the description adds mapping: `filter` maps to vitest --testNamePattern and `path` is an in-tree file/directory, clarifying exact usage. This goes beyond the schema's generic descriptions and helps an agent choose parameters correctly.

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 opens with a specific verb+resource: 'Run the consumer project's vitest test suite,' clearly identifying the tool's action and scope. It further distinguishes itself by stating it supports only vitest projects and that other runners return an error, making it unmistakable from a generic test runner.

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 gives explicit exclusions ('other runners ... return an error until a future council round approves them') and explains how to narrow runs with `filter` or `path`. However, it does not name an alternative tool to use for non-vitest projects, so it stops short of full when-to-use-vs-alternative 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 discloses behavioral traits beyond annotations: it states it is read-only, does not return skill bodies, only names, scores, and personas fraction. The annotation readOnlyHint: true is reinforced and expanded with details about no shell, no writes, and what is returned.

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, front-loaded with the main purpose, and each clause adds value. The mention of the host dropping 402 entries provides context but could be trimmed; still it's justified as it explains why this tool exists.

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 informs the agent what is returned (names, scores, personas) and the read-only behavior. It is complete for a recommendation tool with two parameters that are fully described in schema. The additional context about the catalogue gap adds necessary usage 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?

Schema already fully describes both parameters (task as string, limit with default and min). The description adds that it ranks by a deterministic keyword scorer, which hints at how task is used, but does not significantly enhance parameter understanding beyond the schema. 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 tool matches a free-form task description to relevant skills via a deterministic keyword scorer over SKILL.md frontmatter, and it differentiates from siblings by focusing on task-based search rather than name-based listing (like list_skills). It is specific about verb, resource, and mechanism.

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 when to use: when a skill is not in the catalogue the host delivered, and explains asking by name is impossible while asking by task works. It also implies when not to use (when you can name the skill) and gives a concrete scenario, distinguishing it from 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?

The description states 'Read-only', which is consistent with the readOnlyHint annotation, but goes beyond it by adding a significant non-obvious behavior: 'No-op (empty report) when telemetry recording is disabled.' This is valuable context not available in structured data. It also notes the 'rolling window' aspect, adding operational detail about data recency.

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 exactly two sentences, front-loaded with the main action, and packs in the purpose, usage context, and an edge-case behavior. There is no redundant phrasing or filler. Every clause contributes to understanding, making it appropriately concise 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 read-only tool with one optional parameter and no output schema, the description covers the essential aspects: what the report contains, how it is ranked, when to use it, and what happens when telemetry is disabled. It falls slightly short of a 5 because it does not describe the expected return shape (list, object) or field names, but given the simplicity, it is sufficiently complete for reliable 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?

The schema fully describes the single parameter 'window_days' with a description and default. The description mentions 'over a rolling window' but does not add new details about the parameter itself. Since schema coverage is 100%, the baseline of 3 is appropriate; the description provides minimal additional semantic value beyond what the schema already conveys.

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 a specific verb 'Return' and identifies the resource as the 'arteffect-engagement telemetry report'. It details the content (skills/rules ranked by consult+apply signals) and clearly distinguishes it from sibling tools like list_skills or capabilities_index, which are general artifact listings. The inclusion of 'essential / useful / retirement-candidate' categories further clarifies the specific purpose.

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 sentence 'Use to see which artifacts are actually load-bearing' provides a clear use case for when to invoke this tool. While it does not explicitly name alternatives or exclusions, the focus on telemetry signals implies it is the right choice over generic listing tools. The context is sufficient for an agent to decide appropriately, but lacks an explicit 'when not to use' or alternative tool reference.

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