Ask Claude Code

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

Goes well past the annotations by disclosing data-handling constraints (never credentials, secrets, or customer data), capability boundaries (Claude receives only the prompt, no tool use), statelessness (each call starts a fresh conversation), cost (consumes Claude usage), and result reliability (requested settings echoed, effective model/effort unverified). This is exactly the behavioral context annotations cannot carry.

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?

Front-loads the purpose, then safety, then usage, then caveats. Every sentence carries distinct information; none is filler or restatement of the name.

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 an output schema already documents the return shape, the description covers everything else an agent needs: safety preconditions, capability limits, statelessness, cost, and parameter sourcing. Nothing material is missing.

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%, so baseline is 3, but the description adds meaning beyond the schema: model/effort should be sourced from AGENTS.md guidance, and the response echoes requested settings alongside CLI-reported IDs whose effectiveness is unverified. That clarifies the semantics and limits of these parameters.

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?

States a specific verb and resource — ask Claude Code for a second opinion — and immediately scopes it by noting Claude cannot use tools and that Codex handles code changes. An agent can tell exactly what this call does and does not do.

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?

Gives concrete routing guidance: use it for reviews that return findings and recommendations, while Codex handles code changes, and says to source model/effort from applicable AGENTS.md guidance. No explicit when-not-to-call condition or named sibling tool, but the context is clear.

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