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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it states the output is a complete, compilable file as a string, includes perform() logic and parameter definitions, and explicitly says 'read-only template source; writes no files and uses no network.' This reinforces the read-only nature and clarifies side effects, though it doesn't explore edge cases like invalid IDs.

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 compact yet information-dense. It uses two paragraphs: the first explains core functionality and output format, the second gives usage guidance and effects. Every sentence contributes: what it returns, what's included, when to use it, and side effects. No fluff or repetition of schema details.

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 has one parameter, clear annotations, and an output schema (though its content isn't shown). The description covers purpose, workflow, output composition, and side effects. Given the relative simplicity, the description is complete. It doesn't need to explain return values because there is an output schema, and the description already summarizes the output as a string source file.

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% with a clear description of 'id' (Template id from axint.templates.list, e.g., 'send-message' or 'create-event'). The description adds context about the id's origin and format, and the note 'format changes source versus metadata rendering' hints at potential other inputs. While the schema fully covers the parameter, the description reinforces the critical validation constraint that the id must come from templates.list, adding value beyond the schema.

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 starts with a specific verb ('Retrieve'), names the resource ('full TypeScript source code of a specific bundled template by id'), and clearly contrasts with sibling tools by stating it returns a complete, compilable defineIntent() file. The mention of the workflow with templates.list and compile distinguishes it from list (listing) and compile (compiling), fully clarifying the tool's unique role.

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 usage context: 'Use: use after templates.list to fetch a complete reference template; edit it before calling compile.' This gives a clear workflow and positions it relative to siblings. It also implies when not to use it (no need for source, just metadata/list) and emphasizes that the id must come from templates.list, preventing misuse.

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