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

No annotations are present, so the description carries the burden. It discloses determinism, that results are factual rule matches, that an empty result means 'no configured rule matched' rather than clean code, and that the ruleset is nonexhaustive. It does not discuss performance, permissions, or failure behavior, but the most decision-relevant behavior is covered.

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

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

Four tight sentences cover result, use case, path scoping, and interpretation caveat. There is no filler; each sentence adds actionable 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 an output schema present, return values need no elaboration. The description covers when to use, how to scope paths, how to interpret empty results, and how to reuse the snippet. It would be slightly stronger with explicit guidance on the optional ruleset parameter and differentiation from semgrep_scan_diff, but nothing needed to perform a safe scan is missing.

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 adds real semantics for paths ('Scope paths to the file currently under review') and explains why other-file results are unusable. It gives only indirect context for the ruleset parameter ('The ruleset is broad but not exhaustive') without explaining acceptable values or how the default is treated.

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 opening sentence names a specific operation ('Run deterministic static analysis (Semgrep) over repository files') and a concrete result ('exact line numbers plus the matched source snippet'), so an agent knows what the tool does. It does not explicitly contrast with semgrep_scan_diff or semgrep_status, though 'over repository files' hints at full-repo scope.

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

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

It says when to reach for it: 'Use this to substantiate a suspected defect rather than guessing at it.' It gives a hard scoping rule ('Scope paths to the file currently under review') and explains why ('findings in other files cannot be reported'). It still doesn't name semgrep_scan_diff or semgrep_status as alternatives or state when not to use this tool, so it stops short of full 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?

With no annotations, the description carries the behavioral burden. It discloses determinism, diff-scoping, exclusion of findings on untouched lines, and the output format. It does not explicitly state read-only/no side-effect behavior, but 'static analysis' and 'scan' strongly imply it, so the gap is minor.

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

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

The description is three tightly packed sentences: the core action, the key usage guidance with rationale, and parameter clarification. Every sentence earns its place, with the most important distinguishing detail front-loaded.

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 3-parameter tool with an output schema present, the description covers purpose, selection criteria, parameter semantics, and business context. Nothing needed for an agent to call and interpret this tool correctly is left unaddressed, and the output schema handles return-value 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%, yet the description compensates fully: it explains that base and head are 'any git revisions (`abc123`, `main`, `HEAD~1`)' and that paths is used 'to narrow the scan to specific changed files.' This adds meaning beyond the bare schema titles.

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

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

The description clearly states the specific action ('Run deterministic static analysis (Semgrep)'), the resource ('restricted to the lines changed between two revisions'), and the output shape ('findings with exact line numbers plus the matched source snippet'). It also names the sibling tool it is not, semgrep_scan, making the distinction explicit.

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 directly instructs when to use this tool: 'Prefer this over semgrep_scan when reviewing a pull request.' It explains why with the OpenCodeReview diff-comment constraint and contrasts the tool's behavior ('does not return those at all'), leaving no ambiguity about 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 must carry the behavioral disclosure burden. It clearly describes the nature of the operation as reporting status information and lists the specific elements (binary, version, active ruleset, per-call limits). However, it does not explicitly state whether this call has any side effects, consumes scan quota, or requires authentication, though 'report' strongly implies a read-only operation.

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

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

The description is extremely concise: two sentences with no fluff. The primary purpose is stated first, followed by a succinct list of the reported items, and a clear usage instruction. Every sentence earns its place.

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

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

The tool is simple (no parameters), an output schema exists, and the description explains both what the tool reports and the exact situation in which to call it. Nothing essential is missing for an agent to 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?

The tool has zero parameters, so the input schema is empty. The baseline for parameterless tools is 4, and the description correctly does not need to document any parameters. It adds no parameter information because none exists.

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 reports whether deterministic analysis is available, with a specific verb ('Report') and a well-defined resource (Semgrep status/availability). It enumerates the exact information returned (binary, version, ruleset, per-call limits), making it easy to distinguish from the sibling scan tools semgrep_scan and semgrep_scan_diff.

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

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

The description explicitly says 'Call this once if a scan reports that it is unavailable,' providing a clear trigger condition. It implies this tool is for diagnostic status checks, not for performing scans, but does not explicitly name alternatives or state when not to use it beyond the trigger condition.

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