gograph_wiki

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

Annotations declare readOnlyHint=true, but description states 'Writes files to disk', which implies modification of state. This is an annotation contradiction. Additionally, description does mention destructive behavior (writing files) which contradicts readOnlyHint. No additional behavioral context beyond the contradiction.

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?

Description is front-loaded with purpose and logically structured with 'WHEN TO USE', 'NOT TO USE', 'RETURNS' sections. However, it is slightly verbose; could be more concise by removing repeated listing of file types already implied by the purpose.

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?

Covers prerequisites (requires graph.json, build command), produced files, and return type. However, lacks details about overwrite behavior, idempotency implications, and the exact structure of the return manifest. With no output schema, more details on return format would improve completeness.

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?

Only one optional parameter (output) with schema description covering the default value. Schema description_coverage is 100%, so baseline is 3. The main description does not add further detail about the parameter, but the schema itself is sufficient. No enhancement from description.

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 verb 'Generate the llm-wiki/ directory of machine-first markdown pages from the static graph' and lists all 9 specific file types. It distinguishes from sibling tools by noting that all other gograph tools are read-only, setting this apart as a write operation.

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?

Explicitly provides 'WHEN TO USE: At the start of an agent session on an unfamiliar codebase' and 'NOT TO USE: For targeted symbol lookups (use gograph_context or gograph_source)'. This gives clear context for appropriate vs. inappropriate usage with specific alternatives named.

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