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

Annotations already state readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the agent knows it's safe. The description adds behavior about being a 'quick static check' and mentions cost, but does not disclose the exact nature of findings (e.g., false positives, confidence levels, token limits, diff size constraints) beyond what output schema might imply. Doesn't contradict annotations.

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

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

The description is concise (two sentences) and front-loads the purpose, then adds usage hint and cost. It is efficient but could be more organized with explicit sections (e.g., when to use, limitations). Minor waste on cost which might be better in metadata.

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 a complex tool with 6 params and 0% schema coverage, the description omits critical guidance on parameters like 'focus', 'context', 'language', 'testOutput'—how they affect analysis. It also doesn't mention output format despite an output schema existing (raw JSON vs human-readable). It's a static analysis tool, so higher risk of false positives, but not disclosed. It's adequate for a simple call but not complete for optimal use.

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 does not elaborate on any parameters (diff, focus, context, etc.), but the schema itself provides names and types, and the enum for 'focus' is specified. Since the description doesn't add parameter guidance, it fails to compensate, but it does give high-level purpose. Score 4 would be too high; I set 4 because without any coverage, the description should have explained key params, but it doesn't. I'll re-evaluate: coverage is 0%, so baseline is low; description is insufficient. I'll score 1 because it provides no parameter semantics beyond the raw schema. Actually, I need to be strict: description has zero param details, so score 1.

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 reviews source-code diffs for bugs, missing tests, compatibility, unsafe migrations, and security issues, and notes it returns structured findings with evidence. It distinguishes from siblings by focusing on diff review, though it doesn't explicitly name a sibling like 'migration_safety_auditor' or 'semantic_web_diff' to differentiate.

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 says 'use before merging a patch when you want a quick static check' but provides no explicit guidance on when NOT to use it or alternatives (e.g., migration_safety_auditor for deep migration safety, dependency_risk_scanner for dependencies). It implies usage but doesn't clarify boundaries or integration with CI.

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