gograph_review

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: freshness checking and refresh behavior, CHA/SSA retry on the precise graph, mode-dependent semantics ('Uncommitted modes compare declarations against HEAD, including selected untracked Go files'), and refusal conditions (incomplete comparisons, deleted declarations, missing/ambiguous identities). This is rich behavioral disclosure.

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?

Front-loaded with the core purpose and clearly segmented into WHEN TO USE / NOT TO USE / RETURNS sections, so structure aids scanning. It is somewhat verbose, with internal engine details ('precise and precise_fallback graphs retry CHA/SSA', 'Current-graph consumers refuse...') that are informative but border on excess for a selection-time description.

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 no output schema present, the description compensates by describing the RETURNS shape (changed_symbols[], tests[], routes[], env[], errors[], risk object with public_api/touches_sql/touches_routes/touches_env). Combined with usage rules and refusal conditions, an agent has everything needed for 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?

Schema coverage is 100%, so the schema documents both params and the baseline is 3. The description adds value the schema lacks: it states the mutual requirement ('Requires either symbol or uncommitted=true') and clarifies what uncommitted=true actually reviews ('all current unstaged changes at once'), which is more precise than the schema's 'uncommitted/modified changes'.

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 opens with a specific verb+resource: 'Summarize the scope and risk profile of a change', and immediately enumerates the dimensions covered (changed symbols, covering tests, routes, env vars, SQL). It further differentiates itself from siblings by explicitly naming gograph_boundaries and gograph_plan as alternatives for other jobs.

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?

Contains explicit WHEN TO USE guidance ('After editing — as a post-edit verification step before committing') and a NOT TO USE section routing to gograph_boundaries for boundary enforcement and gograph_plan for pre-edit planning. It also states the invocation condition: 'Requires either symbol or uncommitted=true', and explains the uncommitted=true usage.

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