gograph_context

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint. Description adds 'Read-only; no side effects' and details return behavior (JSON with specific fields, empty object when not found, array with uncommitted). No contradiction with 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?

Single paragraph with structured sections (precondition, when/not to use, returns). Front-loaded with core purpose. Every sentence adds value; no redundancy or fluff.

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 tool with 2 params, rich annotations, and no output schema, the description covers prerequisites, use cases, return structure, and edge cases (empty object, uncommitted array with count). Completely adequate.

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 descriptions cover both parameters (symbol and uncommitted) at 100%. Description adds meaning: symbol can be exact name, dot-notation, or ID; uncommitted bundles context for all modified symbols. Also explains return behavior for uncommitted parameter.

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?

Description clearly states 'Fetch a pre-flight context bundle for a single Go symbol' with specific components (AST metadata, source, callers, callees, tests, role). Distinguishes from sibling tools by noting it eliminates 4-5 separate calls and lists alternative tools for different use cases.

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 WHEN TO USE (first call before editing a symbol) and NOT TO USE (package-level orientation -> gograph_focus; transitive blast radius -> gograph_impact). Also includes prerequisite: requires .gograph/graph.json and gograph build command.

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