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

Annotations already establish read-only, idempotent, open-world behavior. The description adds useful context beyond that: the tools method returns an array of hashes with specific string keys, and the examples clarify that the result can be searched and filtered programmatically. It does not describe edge cases like invalid Ruby, but the annotation coverage makes this a minor gap.

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 longer than many, but every part earns its place: main purpose, usage timing, return structure, and examples. The examples are embedded inline rather than as a separate block, which keeps it compact. Slightly denser than necessary, but highly useful.

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 code-callback tool with no output schema, the description fully explains what the execution context provides, what the returned data looks like, and how to leverage it for exploration. An agent can confidently call this tool to discover endpoints and prepare arguments for api_execute.

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%, but the description significantly extends the meaning of the code parameter with concrete, runnable Ruby examples. It explains how to access the catalog, filter by tag, pull request bodies, and list domains, which is far more actionable than the schema's one-line 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?

The description defines a concrete behavior: discover available Crevio API endpoints, and explicitly positions api_search as the exploration tool used before api_execute. It clearly distinguishes itself from the nearby sibling by naming what it returns and what it is for, leaving no ambiguity about its 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?

The description states precisely when to use the tool: before api_execute, when unsure which endpoint to call, when needing to check parameter names, or when exploring a domain. It also gives concrete examples of queries, so the agent knows what kind of code to build and how to use the tools object.

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