gograph_check

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

Annotations already convey read-only, idempotent, non-destructive hints. The description adds valuable context beyond those hints: it details how relative vs absolute config paths are handled, explains that baselines ending in .json load a saved graph with specific constraints, and notes that Git refs are extracted temporarily. This meaningfully expands the agent's understanding, though it doesn't cover every possible behavior (e.g., error conditions).

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 longer than ideal, with several nested clauses, but it is well-structured with labeled sections (WHEN TO USE, NOT TO USE, RETURNS) and front-loads the main purpose. Each sentence contributes important safety and usage detail, so the length is justified despite being somewhat dense.

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 complex—it aggregates many checks and has nuanced config/baseline logic—and there is no output schema. The description addresses this by listing the checks, explaining config confinement and baseline semantics, and stating the return structure (pass/warn/fail status, findings, summary counts). It is sufficiently complete for an agent to decide when and how to invoke it, though some technical details are compressed.

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 covers all 3 parameters with descriptions, providing a solid baseline. The description adds extra semantic nuance, particularly around config path confinement and baseline handling (saved graph versus Git ref), which maps to the 'config' and 'since' parameters. This goes beyond simply restating the schema, though not every parameter is individually explained in prose.

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 this tool refreshes source analysis and runs static policy checks, enumerating the specific check categories (boundaries, API drift, changed-route/export tests, coverage, etc.). It distinguishes itself from the many sibling analysis tools by serving as a consolidated policy-check/aggregate tool, and the WHEN TO USE/NOT TO USE sections reinforce its intended purpose.

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

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

Provides explicit usage guidance: 'WHEN TO USE: During PR review or pre-commit analysis' and 'NOT TO USE: For CI process exit enforcement (use CLI gograph gate).' This directly tells the agent when to choose this tool over alternatives and even names the specific alternative. It also clarifies config-path confinement for safe usage.

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