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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses significant behavioral traits: it explicitly says 'It does NOT do data-flow analysis', cannot follow values across functions/files, and that empty results are not safety verdicts. It also notes the response lists what it did not analyse, which is rich, actionable 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 appropriately sized and front-loaded; it starts with 'Pattern-based diff linter', then lists the targeted patterns, cites line-level findings, and clarifies limitations and advisory nature. While dense, every sentence is informative and the structure is logical. It loses one point for being slightly long relative to the simplest possible phrasing.

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

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

Despite an existing output schema, the description covers all essential information: what it does, which patterns it flags, how results are presented, what it does not do, and its advisory role. This is complete for an agent to select and invoke the tool correctly without relying on the output schema.

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

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

Schema description coverage is 100%, so the schema already documents the meaning of context, version1, and version2. The description adds only the general diff-linting context, which does not materially enhance parameter understanding beyond the schema. Baseline 3 is appropriate.

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

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

The description defines it as a 'Pattern-based diff linter' that 'flags a fixed set of risky shapes in changed code', then enumerates specific patterns like SQL/shell interpolation, eval/new Function, and empty catch blocks. This is a specific verb+resource (lints diffs for known risky patterns) and clearly distinguishes it from siblings such as diff_text or analyze_responses.

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 states the tool is 'Advisory triage — use a static analyser for a real security gate', providing an explicit when-not-to-use and an alternative. It also clarifies that it does not do data-flow analysis and that an empty result is not a safety verdict, guiding agents on appropriate reliance.

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