gograph_changes

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

While annotations already declare readOnly, idempotent, and non-destructive, the description adds substantial behavioral context: it explains the dual-mode semantics (with and without git_ref), details that 'deleted' in working-tree mode includes absent/ignored/build-inactive files, and notes that without git_ref it compares against trusted persisted graph.json without refreshing. This goes well beyond the structured annotation hints.

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 well-structured with clear labels (WHEN TO USE, NOT TO USE, RETURNS) and front-loads the core action. Each sentence adds information about modes, exclusions, or return values; there is no filler. Despite its length, it remains efficient and easy to scan.

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 the tool's nuance (modes, exclusions, return semantics), the description is complete. It covers what it does, when to use it, behavior in each mode, what it returns (grouped by added/modified/deleted with empty arrays), and explicitly notes it is read-only. No output schema exists, so the description correctly takes on the responsibility of describing return values.

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 only says git_ref is an optional git reference string. The description enriches this by explaining the behavioral difference when git_ref is omitted (uses persisted graph.json) versus provided (refreshes analysis and diffs against the reference). This is crucial semantic information that the schema alone does not convey.

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 and resource: 'List Go symbols that have been structurally modified, added, or deleted.' It clearly distinguishes itself from related tools by explicitly naming git diff for line-level diffs and gograph_impact for blast radius, making the tool's unique purpose unmistakable.

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 provides explicit 'WHEN TO USE' and 'NOT TO USE' sections, stating to use this tool after editing to confirm symbol changes before gograph_impact or gograph_review, and not for line-level diffs (use git diff) or blast radius (use gograph_impact). This is textbook guidance on when and when not to invoke the tool.

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