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

With no annotations, the description carries full responsibility for behavioral disclosure. It only labels the tool as 'EXPERIMENTAL heuristic', which hints at unreliability but does not describe side effects, return behavior, or whether it is read-only. This is insufficient for a tool that might have complex outputs.

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 clear sentence with no wasted words. It is front-loaded with the action and subject, making it easy to parse. However, it is minimal to the point of missing critical details, which slightly lowers the score.

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 provides only a high-level purpose and fails to explain the parameter, expected output, or any operational context. Given the lack of annotations and output schema, this is severely incomplete for an agent to call 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 has 0% description coverage, and the description does not mention the 'path' parameter at all. There is no explanation of what 'path' should point to or its format, leaving the agent completely uninformed about the only required input.

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 builds a data-flow risk map for source and sink patterns, using a specific verb and resource. It is not a tautology and is distinguishable from sibling audit tools, though it doesn't explicitly name alternatives.

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 versus others, nor any exclusions or alternative tools. The single-sentence description offers no contextual triggers or prerequisites.

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 destructiveHint=false, so the safety profile is covered. The description adds the polling behavior, which is genuinely useful beyond annotations, but it does not explain what 'terminal' means, what the response contains, or any side effects (e.g., state changes between polls). Since it adds some behavior context but not full transparency, 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?

The description is two short sentences with no filler. The core purpose ('Review the complete bound workspace') is front-loaded, and the polling instruction is a necessary operational detail. It could arguably be more structured (e.g., listing return behavior), but it is appropriately concise for the amount of information it conveys.

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 a rich output schema (which likely explains the 'terminal' state and review results), so the description does not need to detail return types. However, the phrase 'until terminal' is ambiguous without context on how to recognize terminality, and the description does not clarify the scope of 'complete bound workspace' or what 'review' entails (e.g., security, code quality, dependencies). Given the complexity of a polling-based review, the description is minimally complete but leaves gaps that the schema and sibling definitions may or may not fill.

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 documents both parameters fully (100% coverage), including the meaning of 'path' ('checks the project path; use '.' for the fixed workspace') and 'include_flow' (whether to run input/processing/external transmission flow analysis). The description adds nothing about parameters beyond what the schema provides, so the 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 specifies a clear verb ('Review') and a resource ('the complete bound workspace'), so an agent can deduce the tool's core function. It also hints at a distinctive workflow (polling with continue_review) that sets it apart from simpler scans, but it doesn't explicitly name or contrast siblings, so it stops short of a 5.

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 instruction 'poll with continue_review until terminal' gives a usage pattern, implying this is a long-running operation and that continue_review is the follow-up tool. However, it does not state when to prefer this over alternatives like scan_workspace or start_review_before_ship, nor does it give exclusions or prerequisites. The guidance is implicit 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 already indicate read-only, idempotent, and non-destructive behavior. The description adds valuable context about the iterative waiting mechanism and the terminal states, which goes beyond what annotations declare. This clarifies that multiple calls may be needed and defines the loop exit condition without contradicting the 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, front-loaded sentence that captures the essential behavior and stop condition. It contains no redundant details, and for a tool with 5 parameters, the schema fully covers parameter specifics, so brevity is both appropriate 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?

The description conveys the core polling loop and terminal decisions, sufficient for an agent to understand the call pattern. With annotations covering safety and schema covering parameters, the description need not list parameters or response format. It could be more explicit about error handling or max retry expectations, but for a standard polling tool this is adequately 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 detailed per-parameter descriptions (e.g., wait_seconds limits, finding_limit range), so the description adds no parameter-level value. As per baseline for high schema coverage, a score of 3 is appropriate since the description effectively delegates parameter comprehension to 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 states a clear action ('Wait briefly') and a specific resource ('a long review') with an explicit termination condition ('until state is completed or failed'). It distinguishes itself from sibling start_review_before_ship by being the polling/waiting counterpart, making its role 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 implies a polling loop but does not explicitly state when to call it, such as after start_review_before_ship or check_my_app. It lacks any mention of alternative tools or exclusion criteria, leaving preparation and sequencing to caller inference. The schema's review_id description helps but is not part of the tool description itself.

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 only says 'Create' without disclosing side effects, such as whether it overwrites an existing file, what the return value looks like, or any permission requirements. The description adds no behavioral context beyond the trivial fact of creation.

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 with no waste. However, it is too terse, sacrificing necessary detail for brevity. Front-loading is acceptable, but the cryptic '20/20/10' and lack of any explanation reduce its effectiveness.

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 annotations, the description should at least explain what a 'benchmark manifest' is, whether the file is created or overwritten, and any output expectations. The description lacks these details, making it incomplete for an agent to use correctly without prior domain knowledge.

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 only one parameter, output_path, with zero description coverage. The description does not mention the parameter at all, so an agent has no information about the expected format, whether it's a directory or full path, or the file name conventions. The description fails to compensate for the lack of schema 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 states a clear verb ('Create') and a specific resource ('20/20/10 field benchmark manifest CSV template'). The 'benchmark' keyword distinguishes it from sibling template tools like create_field_campaign_template and create_guardian_manifest_template. It is specific but leaves the meaning of '20/20/10' unexplained, so not a 5.

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 versus the sibling template tools. There is no mention of alternatives, exclusions, or selection criteria. An agent would have to infer usage from the name alone, which is not sufficient when similar templates exist.

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 full responsibility for disclosing behavioral traits. It only says 'create', which is generic and matches the tool name; it does not mention whether the operation is destructive, whether it overwrites existing files, what permissions are required, or what success/error responses look like. The description adds minimal value beyond the tool name.

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 (a single sentence) with no wasted words. However, it is so terse that it omits essential details, making it under-specified rather than efficiently structured. It is neither bloated nor well-organized; it simply lacks substance.

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 one parameter, no output schema, and no annotations, the description should at least clarify what 'empty roster' means, what output_path should point to, and any prerequisites or side effects. The description only gives a vague workflow hint ('before holdout preregistration') and leaves the main operational details undocumented, making it insufficient for a correct call.

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 no parameter descriptions (coverage 0%) and the tool description does not mention the 'output_path' parameter at all. Even though the parameter name is somewhat self-explanatory, the description fails to elaborate on expected format, path conventions, or default behavior. The description offers zero assistance for correct parameter usage.

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 a specific verb ('Create') and a specific resource ('empty 12-20 app owned/partner roster'), and gives a context cue ('before holdout preregistration'). It is clear about what the tool does, though it does not explicitly contrast with sibling template creators like create_benchmark_template or create_guardian_manifest_template. The purpose is distinguishable by the unique resource 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 phrase 'used before holdout preregistration' implies a temporal context but does not give explicit when-to-use vs when-not-to-use guidance, nor does it mention any alternative tools or conditions for choosing this tool over a sibling. There is no guidance on preconditions or expected workflow.

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 no annotations provided, the description carries the full burden of disclosing side effects. It says 'create' but does not describe whether the tool overwrites existing files, requires specific permissions, or produces a specific return value. The lack of behavioral detail (e.g., idempotency, error conditions) leaves the agent without important operational 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 a single, focused sentence that is front-loaded with the action. It is concise without padding, but its brevity comes at the cost of missing critical details, making it more under-specified than efficiently 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?

For a mutation tool that creates a file, with no annotations, no output schema, and no parameter documentation, the description is far from complete. It omits details about the manifest structure, default behavior, and parameter semantics, which an agent would need to invoke the tool correctly and safely.

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 0%, so the description must compensate by explaining the output_path parameter. It does not: the description only mentions the manifest creation and gives no guidance on the expected format, constraints, or usage of output_path. The parameter name is self-explanatory but the description adds no additional semantic value.

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 'Create' and the resource 'a korean_senior Guardian manifest', and adds the specific context of 'four-domain pre-release reviews.' This distinguishes it from sibling template tools like create_benchmark_template and create_field_campaign_template, 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 implies usage for pre-release reviews but does not explicitly state when to use this tool versus similar template creators, nor does it mention any exclusions or alternatives. An agent would have to infer the use case from the name and description, lacking explicit routing 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 are absent, so the description carries the full burden of behavioral disclosure. It only says 'Run' the gate, without stating whether it is read-only, destructive, requires specific inputs, or what happens on failure. With 14 parameters and no cautions, the agent has no idea of side effects or prerequisites—a serious 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 a single, concise sentence that front-loads the action and lists evidence categories. There is no filler or redundancy. However, given the tool's complexity, it is overly terse, though conciseness itself is well-handled.

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 14 required parameters, no annotations, no output schema, and no parameter descriptions, the description is grossly incomplete. It fails to explain what each path is for, what the gate checks, success criteria, side effects, or output format. An agent cannot confidently invoke this 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 description coverage is 0%, so the description must compensate. It groups evidence into Guardian, validation, Korean corpus, and MCP interceptor categories, which helps map high-level intent but does not explain the 14 specific path parameters, their expected formats, or relationships. This is insufficient for an agent to correctly populate all required fields.

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 a specific verb 'Run' and resource 'strict data shipment gate', and lists the evidence sources (Guardian, validation, Korean corpus, MCP interceptor). It is clear what the tool does overall, though it does not explicitly differentiate from sibling tools like security_gate or guardian_audit. The distinctive evidence components give some differentiation, hence a 4.

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. It omits prerequisites, exclusions, or context clues such as 'use this before shipping data' or 'do not use if X'. The agent must infer usage from the tool name and stack. This is a significant miss for a tool with many related 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?

With no annotations, the description carries the full burden but only discloses a few behavioral traits: 'fail-closed' and 'intrafile evidence, not an authorization proof'. These are useful, but it does not mention permissions, side effects, rate limits, or output behavior. It adds some context beyond the schema but leaves many aspects undisclosed.

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—one sentence with two clauses—and front-loads the action. Every word earns its place, but the brevity leaves essential details missing, so it is efficient but not optimally informative.

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 that this is a security audit tool with only one parameter and no output schema, the description is incomplete. It does not explain the return value, the exact meaning of 'workspace_path', prerequisites, or how the result relates to other tools. The caveats about fail-closed and non-authorization are helpful, but the agent lacks critical operational details.

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 0%, so the description must compensate for the parameter 'workspace_path', but it provides no explanation of what this parameter expects, its format, or its purpose. The agent has no additional information beyond the variable name, making it difficult to invoke 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 states a specific action ('Run the local fail-closed Semgrep deep profile') and a clear resource (Semgrep deep profile), with an additional qualifier about its scope ('intrafile evidence, not an authorization proof'). It is clear about what the tool does, though it does not explicitly differentiate from sibling tools like scan_workspace or software_composition_audit.

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. The phrase 'intrafile evidence' hints at a single-file analysis scope, but it does not state conditions or mention sibling tools. No exclusions or alternative routing 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?

No annotations are provided, so the description must carry all behavioral disclosure. It mentions 'report-only' (non-destructive) and 'raw-free' (does not expose raw data), which are helpful, but it does not clarify whether any state is modified, whether authentication is needed, or the exact nature of the interceptor result. The disclosure is partial despite carrying the full burden.

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 with the primary action front-loaded. It is concise and avoids filler, though it may be too terse for the tool's complexity. In terms of structure, it communicates the core action efficiently.

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, no annotations, minimal parameter documentation, and a relatively complex policy-evaluation task, the description is severely incomplete. It fails to explain the interceptor result, parameter semantics, or any side effects, leaving the agent without enough context to 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?

Schema description coverage is 0% and the description does not explain the purpose of the 'text' or 'label' parameters. An agent cannot infer what text to pass or how label affects the call. The description adds no meaning beyond the generic parameter names.

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 ('Evaluate') and resource ('MCP runtime block/redact policy') and indicates the output type ('raw-free report-only interceptor result'). It distinguishes from siblings like observe_mcp_event (observation) and scan_mcp_config (scanning), though 'raw-free' and 'interceptor' are jargon that could confuse agents.

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 its siblings. It does not mention alternatives, exclusions, or prerequisites. The only implicit signal is the verb 'Evaluate' suggesting policy enforcement, but nothing clarifies a selection condition.

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, idempotentHint, and destructiveHint, covering the safety profile. The description adds that the tool provides impact, fix steps, and verification, which is useful context beyond a generic 'explain'. However, it does not disclose output format, error handling, or any other behavioral traits, so the added value is moderate.

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 sentence that front-loads the action and lists the key outputs. There is no fluff, and it is concise without being under-specified—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?

For a simple tool with one parameter and annotations covering safety, the description is minimal but conveys the purpose. However, it lacks usage guidance and parameter semantics, and it does not contextually place itself among the many sibling tools. An agent would not know when to call it or how to find the rule_id, leaving notable 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 schema provides only the parameter name 'rule_id' with type string and no description. The tool description does not explain what a rule_id is, how to obtain it, or its format. With 0% schema description coverage, the description wholly fails to compensate, leaving the agent with no semantic context for the sole required parameter.

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 a specific action ('Explain a K-Guard rule') on a specific resource, and lists the content of the explanation (impact, fix steps, verification). This distinguishes it from siblings like suggest_fix, which focuses on proposing fixes rather than explaining a rule.

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 suggest_fix or scan_workspace. It does not mention why one would prefer an explanation over a fix suggestion, nor any conditions or prerequisites, leaving the agent to infer usage.

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 no annotations provided, the description must convey behavioral traits such as side effects, return values, or error conditions. It only discloses that probes need explicit opt-in and that results are aggregated by cohort. It does not describe what the tool returns, whether it is read-only, or any side effects. The sparse disclosure leaves the agent uncertain about the tool's full 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 two short sentences with no redundant wording. The primary action is stated first, followed by a specific constraint. Every word adds some value, and the structure is front-loaded with the main 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?

Given three parameters, no output schema, and no annotations, the description is insufficient. It does not explain what manifest_path should reference, what run_probes does beyond the opt-in hint, or the role of review_path. An agent would need external knowledge to invoke this correctly. The description covers only a fraction of the necessary context for a tool of this 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?

The input schema has 0% description coverage, so the description must explain the parameters. It does not define manifest_path, run_probes, or review_path beyond their names. The mention of cohort and probe opt-in hints at some parameter usage, but not enough for an agent to correctly fill in all parameters without further knowledge. The description compensates poorly for the missing schema 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 states a specific verb ('Aggregate') and resource ('field benchmark reports') with a clear qualifier ('by cohort'). It distinguishes the tool from siblings like create_benchmark_template or field_campaign_status, which deal with creation or status rather than aggregation. The probe opt-in clause adds a specific characteristic, but the description does not explicitly name any sibling for comparison.

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 no guidance on when to use this tool over alternatives. It states a requirement about probes ('probes require explicit MCP probe opt-in') but does not explain when aggregation is appropriate or when to choose another tool. There is no mention of context, prerequisites, or exclusions.

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 no annotations, the description must disclose behavior. 'Fail-closed' hints at error handling but doesn't explain side effects, required permissions, or what happens on failure. 'Raw-free' suggests output transformation but is undefined.

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 with no waste, but it sacrifices substance for brevity. It is concise in length but not in delivering necessary 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 two required parameters and no output schema, an agent cannot infer what output looks like, what 'raw-free' means, or what 'fail-closed' implies. The description is inadequate for safe 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 0%, so the description must define both required parameters. It never mentions roster_path or output_path, leaving their purpose entirely unclear.

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 identifies a specific action ('validate') and resource ('app roster'), with a defined outcome ('emit a campaign status'). It is distinct from sibling validation tools by focusing on campaign 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?

No guidance is given on when to use this tool versus alternatives like validate_policy_controls or scan_workspace. It does not state prerequisites, exclusions, or selection criteria.

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?

Since no annotations are provided, the description must carry the full burden of behavioral disclosure. It does reveal two behaviors: the requirement for four review domains for korean_senior rows and the fail-closed behavior when fail_on is set. However, it does not disclose whether the tool is read-only, what it modifies, any authentication requirements, or any side effects. This is insufficient for an audit tool of this complexity.

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 combines two unrelated pieces of information with a semicolon. It is concise but severely under-specified for a tool with 9 parameters. The structure does not front-load the most important information about the tool's purpose or usage; instead it focuses on an edge case about korean_senior rows.

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 9 parameters, no annotations, and no output schema, the description is drastically incomplete. An agent has no understanding of what the tool returns, what most parameters do, or what the audit covers. The description only addresses a narrow scenario, leaving the agent to guess about the rest.

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 0%, so the description should compensate by explaining key parameters. It only hints at 'fail_on' by mentioning it in the fail-closed clause, but does not explain its values or purpose. Parameters like run_sca, run_probes, and various report paths are left completely unexplained, making it hard for an agent to know how to set them.

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 'Run Guardian' which identifies the action, but it does not explain what Guardian does or why it would be used. The mention of 'korean_senior rows' and 'four review domains' suggests a specific audit context, but without knowing what Guardian does, the purpose remains ambiguous. It distinguishes from siblings only by name, not by functionality.

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 a specific condition: 'korean_senior rows require four review domains' and 'fail closed when fail_on is set.' This hints at when this tool might be needed, but it does not explicitly state when to use this tool over alternatives like deep_analyzer_audit or software_composition_audit. There is no guidance on exclusions 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?

With no annotations, the description carries the full burden of behavioral disclosure. It mentions 'observe' which hints at read-only, but does not state whether the tool has side effects, modifies state, requires specific permissions, or what 'stream-ready block/redact policy decisions' entail. The description is too vague to inform an agent about side effects or constraints.

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 front-loads the core action and output. It is concise with zero wasted words, making it easy to parse quickly.

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 3 parameters, no output schema, and no annotations, the description is incomplete. It does not explain how to construct the input, what the return value looks like, or any operational context (e.g., streaming behavior, policy format). An agent calling this tool would lack essential details to use 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?

Schema description coverage is 0%, meaning the schema provides no explanation for parameters. The description does not compensate by explaining the role of 'text', 'label', or 'session_id'. There is no guidance on what content to pass or how these parameters influence the output. This is a significant gap for a 3-parameter tool.

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 a specific verb ('observe'), a specific object ('one MCP runtime event'), and the result ('return stream-ready block/redact policy decisions'). It clearly differentiates from sibling tools like observe_mcp_events (plural) and enforce_mcp_events by emphasizing the singular scope and the decision-returning 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 explicit guidance on when to use this tool versus its siblings. The description implies usage for a single event but does not state when to prefer it over observe_mcp_events or enforce_mcp_events. No exclusions or alternative conditions are provided, leaving the agent to infer the 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does explain that the tool scans for PII, hidden instructions, and agentic/external flow, which gives insight into its function. However, it does not explicitly state whether the tool is read-only, has side effects, or requires network access. The term 'observe' implies passivity, but this is not confirmed.

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-structured sentence that delivers the core purpose upfront and appends the specific detection targets. It contains no superfluous words and is highly efficient, making it easy for an agent to parse quickly.

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 absence of an output schema and annotations, the description should at least hint at what the tool returns. It does not mention output format or return values. Additionally, it fails to explain the role of the optional 'label' parameter. For a tool with only two parameters, the description is reasonably complete for the primary action but leaves critical context gaps for a fully informed call.

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 description coverage is 0%, so the description must compensate for parameter clarity. The description implies that the 'text' parameter contains JSONL events (from 'Observe MCP runtime/proxy JSONL events'), but it does not explicitly map description content to parameters, and the 'label' parameter is completely unexplained. This leaves the agent uncertain about parameter formatting and purpose.

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 (observe) and the resource (MCP runtime/proxy JSONL events) and specifies the focus (PII, hidden instructions, agentic/external flow). This distinguishes it from sibling tools like 'observe_mcp_event' (singular) and 'enforce_mcp_events' (different action) without needing to inspect their schemas.

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 any guidance on when to use this tool versus alternatives. It does not mention specific scenarios or indicate conditions where a different tool would be more appropriate. No exclusions or alternative references are given.

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 no annotations provided, the description carries the full burden of behavioral disclosure. It does state 'safe read-only', indicating non-mutating behavior, and restricts targets to localhost or authorized external, which is useful. However, it fails to disclose behaviors related to parameters, response format, authentication needs, or rate limiting, leaving significant gaps.

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 core purpose and target constraint. It avoids redundancy and is easy to parse. However, it is perhaps too brief given the other gaps, but for conciseness alone it is strong.

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 5 parameters, no output schema, and no annotations, a complete description would need to cover parameter semantics, expected return values, and use cases. This description only provides a high-level purpose and target restriction, leaving the agent without enough information to call the tool correctly. It is substantially incomplete.

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 0%, so the description must compensate by explaining parameters. It offers no explanation for any of the five parameters (base_url, deep_active, session_file, authorization_note, external_authorized). The agent cannot infer their meaning or usage from the description, which is a severe deficiency.

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 identifies the tool as a read-only HTTP prober with specific target constraints (localhost or explicitly authorized external targets). It uses a concrete verb ('Run') and a resource ('HTTP probes'), making the purpose unambiguous. While it doesn't name a sibling, no sibling tool appears similar, so it stands alone 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?

The description implies use for probing HTTP endpoints but provides no explicit scenarios, alternatives, or exclusions. It does not mention when to prefer another tool or when this tool should not be used. The guidance is inferred from the purpose statement rather than directly stated.

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 no annotations, the description carries the full burden of behavioral disclosure. It states that raw diff content is not echoed, which is a meaningful behavior. However, it does not describe what the tool does return, whether it is read-only, or any side effects. For a scan tool, this is a partial disclosure; more detail on the output format would improve 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?

The description is a single, focused sentence that front-loads the core purpose and the key behavioral absence. It is concise with no redundant wording. However, given the tool's parameters and lack of annotations, it may be slightly under-specified, but it earns its place as an efficient opening statement.

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 three parameters, no output schema, and no annotations. The description does not explain parameter semantics, expected output, or usage context beyond the scope of a git diff. An agent would lack crucial details to invoke the tool correctly, making the description inadequate 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?

Schema description coverage is 0% (no parameter descriptions), so the description must compensate. It does not mention base_ref, head_ref, or workspace_path at all. The parameter names and defaults in the schema give some hints, but the description adds no additional meaning, leaving an agent unsure how to set the refs or workspace path 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 clearly identifies the resource (a git diff) and the action (scan), and adds a specific behavioral distinction ('without echoing raw diff content in the MCP response'). This unmistakably differentiates it from sibling scan tools like scan_workspace and scan_text, 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?

The description implies when to use this tool (for scanning a git diff) but does not explicitly mention alternatives or exclusions. An agent can infer the primary use case, but there is no guidance on when NOT to use it versus scan_workspace or scan_text. The scope is clear enough to make an inference, so it is not a complete miss.

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 of behavioral disclosure. 'Discover and scan' implies a read operation, but it doesn't state whether it modifies anything, what it returns, how thorough the scan is, or whether it only scans the given path. There is no disclosure of potential side effects or performance implications. Minimal value beyond the literal meaning.

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, which is concise and front-loads the main verb. However, it is under-specified rather than efficiently detailed. Every word is used, but the ambiguity (e.g., 'discover and scan' vs just 'scan') means the sentence doesn't earn its place as the sole 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?

Given the absence of annotations and output schema, the description must explain the tool's return value and behavior. It does not mention what the scan produces (list of files? config contents?), how to interpret results, or whether the path is required (though default '.' is in schema). For a tool that likely serves as an inventory/analysis entry point, the description is incomplete.

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 one parameter 'path' with no description and 0% schema coverage. The description does not explain what 'path' refers to (directory root? file?) or how it affects the scan. Since the schema provides no semantic help and the description adds nothing, parameter understanding is left to guessing.

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 clear verb+resource pattern ('Discover and scan project MCP configs plus agent instruction and skill components'), which states what the tool does. It is specific enough about the resource type to distinguish from generic scan tools like scan_workspace, but it doesn't fully delimit scope (what counts as 'agent instruction and skill components' is vague). Not a tautology, but could be sharper.

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 mention of when to use this tool versus the many sibling scanning tools (scan_workspace, scan_text, scan_diff, etc.). No context about typical use cases, prerequisites, or exclusions. The description offers no guidance on 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose one meaningful trait: the operation does not write to disk. But it doesn't mention whether the scan is read-only, what side effects or requirements exist, or what the return format is. This is partial disclosure, but not comprehensive.

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 leads with the primary action and key constraint. Every word adds value, and it avoids redundant phrasing. It is appropriately sized for a 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 the tool's simplicity (2 params, no output schema), the description covers the core behavior but leaves gaps: parameter semantics are unexplained, and differentiation from sibling scan tools (scan_workspace, scan_diff, etc.) is only implicit. An agent might not know exactly when to choose this over alternatives without additional 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 description coverage is 0%, and the description provides no information about the parameters. While the names 'text' and 'label' are fairly self-explanatory, the description does not clarify expected formats, defaults, or how the label is used. The description fails to compensate for the lack of 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 states the verb 'scan' and the resource 'inline text snippet', clearly distinguishing it from file- or workspace-based scans. However, it doesn't specify the type or goal of the scan (e.g., security, content analysis), leaving some ambiguity about what the scan actually does.

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 'inline text snippet' and 'without writing it to disk' strongly imply the intended use case: scanning text passed directly rather than from a file. However, it doesn't explicitly name alternative tools (e.g., scan_workspace, scan_diff) or state when those would be preferred, so the usage guidance is 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It does not state whether the scan is read-only, whether it modifies files, what 'flow risks' entail, or what the return format looks like. The tool appears to be a scan, but its side effects and operational implications are opaque, which is a significant gap for a security-related 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 with no wasted words. It leads with the action and resource, then lists the detection categories. It is efficient, though it could be improved by adding a sentence about parameters or usage without becoming 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?

Given the tool's complexity (scanning a whole workspace for multiple risk types) and the absence of an output schema and annotations, the description is insufficient. It does not explain what results are returned, how to interpret them, or the role of the include_flow parameter, leaving an agent with significant uncertainty about how 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?

With 0% schema description coverage, the description must explain each parameter, but it only indirectly references 'path' via 'local workspace' and completely omits the 'include_flow' boolean. An agent would not know what toggling 'include_flow' does or why it defaults to true. The description fails to compensate for the schema's lack of 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 states a specific verb ('Scan'), a resource ('local workspace'), and enumerates the exact categories it detects (secrets, Korean PII, composite PII, config risks, flow risks). This clearly distinguishes it from sibling tools like scan_text or scan_diff that operate on different input types, so an agent can immediately tell what this tool is for.

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 context (scanning a directory) via the phrase 'local workspace' and the required 'path' parameter, but it does not explicitly state when to choose this over alternatives like scan_text or scan_diff, nor does it mention any prerequisite conditions. The guidance is present but 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?

With no annotations provided, the description carries the full burden. It mentions returning a scoreboard but does not disclose whether the operation is read-only, whether it modifies the corpus, requires specific permissions, or has side effects. The lack of explicit safety cues 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?

A single sentence front-loads the core purpose and output. Every word is informative with no filler, earning a top score for efficiency and clarity of structure.

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 (one required param, no output schema), but the description lacks essential context: required input format, what constitutes a corpus, and any prerequisites. With no annotations to fall back on, this is not complete enough for confident 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 0%, so the description must explain the 'corpus_path' parameter. It only hints at 'local fixture corpus' without specifying path format, file/directory requirements, or any constraints. This is insufficient for an agent to determine correct input.

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 a specific verb ('Evaluate'), a clear resource ('local fixture corpus'), and an explicit output ('FP/FN precision/recall scoreboard'). It uniquely identifies this tool among siblings, which are focused on scanning, validation, and audits rather than scoring a fixture corpus.

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 about when to use this tool versus alternatives or any exclusions. The description only states what it does, leaving the agent to infer applicability without any contextual cues or usage conditions.

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, idempotentHint=true, and destructiveHint=false, covering mutation safety and side effects. The description adds 'quick' and 'workspace' context, which is slightly beyond annotations. However, it does not disclose what the gate actually does (e.g., what it scans, how it reports failures, whether it touches files). With annotations present, a 3 is appropriate – it adds minimal context but does not contradict or amplify the safety profile.

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 short (two sentences) and front-loaded with the action, but it is under-specified. There is no wasted wording, yet the conciseness does not earn its place because it conveys almost no actionable information. A description this brief would be acceptable only if the schema and annotations carried the load, but they do not for parameters and 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?

The tool has no output schema, no parameter descriptions, and a minimal description. There is no explanation of what the gate checks, what fail_on levels mean, what include_flow does, or how results are returned. Even with annotations, the agent lacks essential context to decide when and how to call this tool correctly. The description is far from complete for a security gate with three 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?

Schema description coverage is 0%, and the tool description does not mention any of the three parameters (path, fail_on, include_flow). The agent must rely purely on parameter names and defaults, which is insufficient for correct invocation. The description completely fails to compensate for the lack of schema descriptions, leaving parameter semantics entirely unexplained.

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 'Run the quick workspace gate' – a verb and resource, but 'workspace gate' is vague and does not specify what checks are performed, what outcomes are produced, or what 'gate' means in this context. It distinguishes from guardian_audit but does not define its own purpose clearly. A more specific statement like 'Run a lightweight security scan on the workspace' would be clearer.

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 names guardian_audit as the canonical release gate, implying this tool is for a quicker, non-canonical check. This is partial guidance – it tells the agent when *not* to use this tool (for canonical releases) but does not state conditions for when to use this tool itself. It lacks direct 'use this when...' language, but the alternative reference provides some routing.

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 discloses a key behavioral trait: explicit authorization is required because engines may consult advisory databases, implying external network access. However, it does not state whether the tool modifies files or only reads, nor does it describe any other side effects. The disclosure is useful but incomplete.

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 front-loads the core purpose and then adds the critical authorization note. There is no fluff or redundancy; every word contributes to understanding the tool's function and a key prerequisite.

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 incomplete for a tool that audits lock files. It does not explain what 'audit' means in terms of output (e.g., vulnerability report, risk score), what happens during the audit, or how parameters like 'authorize_advisory_lookup' affect behavior. With no output schema and only minimal description, an agent would struggle to correctly invoke and interpret results.

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 0%, so the description must compensate. It barely touches on the 'authorize_advisory_lookup' parameter via the authorization mention, but it does not explain either parameter's purpose or how to set them. The description adds minimal value beyond what the schema shows (names and defaults). This is insufficient for a tool where parameters are not self-explanatory.

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 audits Python/npm/Go locks, specifying the verb 'audit' and the target resources. It distinguishes from generic audit tools like deep_analyzer_audit by focusing on lock files for specific ecosystems. However, it does not explicitly name sibling alternatives, so it falls short of a 5.

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: use when you need to audit lock files for Python, npm, or Go. It does not provide explicit when-not guidance or mention alternatives, but the scope is clear enough to infer the primary use case. No exclusions or alternative suggestions are given.

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 of behavioral disclosure. It does not reveal what side effects occur, whether the action is destructive, what permissions are needed, or what operational impact 'starting Guardian high' has. The tool appears to be a state-changing action with zero 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?

The description is a single sentence, which is concise but grossly under-specified. It omits essential information and does not front-load any useful detail. Conciseness without substance is not effective.

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 complexity (14 parameters, 6 required) and an output schema, the description needs to explain the tool's purpose, return value, and usage context. It does none of that. The single sentence leaves an agent without enough information to know when or how to 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?

Schema description coverage is 100%, so the schema already documents all 14 parameters. The description adds no parameter-specific meaning, which aligns with the baseline of 3 when 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 says 'Start Guardian high' but never defines what 'Guardian high' is. It mentions a precondition (after a completed first review) but does not state the tool's actual function, resource, or outcome. This is vague and could be confused with sibling tools like continue_review or guardian_audit.

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 one usage condition (only after a completed first review) but gives no guidance on when to use this tool versus siblings like check_my_app, continue_review, or guardian_audit. There is no mention of alternatives or exclusions beyond the single prerequisite.

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 idempotentHint=true, so the description correctly aligns by stating 'dry-run,' which implies no changes are applied. However, it does not mention any additional behavioral aspects like rate limits, required authentication, or the shape of the response. It adds a small amount of context about being a dry-run but stays within the safety profile the annotations already establish.

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, focused sentence that states the core functionality without any filler. The key concept (dry-run fix recipe) is front-loaded, and there is zero 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 relative simplicity (two parameters, read-only operation) and the presence of safety annotations, the description covers the basic operation. However, without an output schema, the agent does not know what a 'fix recipe' or 'regression-test suggestions' looks like, and the framework parameter's effect is unaddressed. This makes the description incomplete for a 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?

The schema has no descriptions for rule_id or framework, and the description only refers to 'a rule,' which indirectly hints at rule_id but does not explain what a rule is or how framework modifies the output. With 0% schema coverage and no parameter explanation, the description fails to compensate, leaving the agent to guess at the meaning and semantics of both 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?

States a clear action (return) and a specific object of that action: a dry-run fix recipe and regression-test suggestions for a rule. It distinguishes itself from siblings like explain_rule by focusing on fixes rather than explanations, though it does not explicitly name alternatives.

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 no explicit guidance on when to choose this tool over the many siblings, such as explain_rule or scan tools. The only implicit usage is that it applies to a rule, but there is no information about prerequisites, contexts, 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?

With no annotations provided, the description is the sole source of behavioral disclosure. It discloses that the tool runs twice and explicitly states it does not claim field accuracy, which is a useful limitation. However, it does not describe side effects, return values, or what the validation process actually does beyond running twice, leaving significant behavioral gaps.

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, efficient sentence that front-loads the action and includes a caveat. It contains no redundant words or unnecessary detail, making it concise and 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?

Given the tool has one parameter and no output schema, the description should explain what pack_path should point to, what running twice accomplishes, and what the expected output or result indicates. The description only instructs to run it twice and disclaims accuracy, which is insufficient for an agent to invoke it correctly without guessing.

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 one parameter (pack_path) with 0% description coverage, meaning the schema provides no meaning. The tool description does not mention the parameter at all, offering no context about what path to supply, its format, or its purpose. The description completely fails to compensate for the missing schema 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 states a specific action ('Run the pinned nine-language pack twice') on a named resource, making the primary action clear. The tool name 'validate_multilang_pack' reinforces the purpose of validation, and the caveat 'does not claim field accuracy' differentiates it from accuracy-focused tools. However, it does not explicitly state that it validates a multilingual pack, relying on the name for that.

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 siblings like validate_policy_controls or scan_workspace. It does not mention prerequisites, scenarios, exclusions, or alternatives. An agent has no basis for choosing this tool over others.

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 no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'Run', implying execution but does not state side effects, whether it is read-only, what output it produces, or any dependencies. The phrase 'repeated synthetic' hints at repetition but remains vague and unexplained.

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 with no redundant words. It front-loads the primary action and resource. While it lacks structure or headers, it is efficient and easy to read for its length.

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 lacks an output schema, annotations, and rich parameter documentation. The description gives only a terse summary that assumes domain knowledge about JIT/JEA and AST/RBAC. It does not explain what the validation entails, what the output looks like, or any prerequisites, leaving the agent under-informed for a validation/control 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 0% and the description does not mention the sole parameter 'output_path' at all. The parameter name suggests it is an output destination, but that is not clarified. The description adds no meaning beyond what the schema already shows, and fails to compensate for the lack of schema 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 states a clear action ('Run') and a specific resource ('the repeated synthetic JIT/JEA and database AST/RBAC/isolation control pack'). It provides enough specificity to distinguish it from siblings like validate_multilang_pack, though the jargon-heavy phrasing ('synthetic JIT/JEA' and 'AST/RBAC/isolation') may be ambiguous without domain context.

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 versus alternatives. It does not mention any sibling tools, conditions, or exclusions. The description simply states what it does, leaving the agent to infer context from the name and context signals.

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 no annotations provided, the description carries the full burden of behavior disclosure. It only says it 'runs' something, without disclosing side effects, read-only vs mutating nature, auth requirements, or output format. This is a serious gap for a tool that likely performs complex validation.

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 short sentence, but it is under-specified rather than concise. It contains almost no actionable information, so the words do not earn their place. It is more of a heading than an explanation.

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 that likely executes a multi-faceted validation matrix, the description provides no context on what the matrix entails, how to interpret results, or how the output_path is used. With no output schema and minimal description, an agent cannot confidently call this 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 only parameter, output_path, has 0% schema description coverage and the description does not mention it at all. The description adds no meaning to the parameter, failing to compensate for the schema's lack of 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 states a specific verb ('Run') and resource ('Streamable HTTP'), and lists topics it covers (authorization, lifecycle, SSE, audit). However, 'repeated ... matrix' is vague and does not clearly convey what the tool actually does. It does not explicitly differentiate from sibling validation tools like validate_policy_controls or validate_multilang_pack, but the resource name gives some distinction.

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 no guidance on when to use this tool versus its siblings. It does not mention prerequisites, scenarios, or exclusions. An agent would have no cue for choosing this over other validation tools.

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