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

Adds valuable context beyond annotations: clarifies no existing credential is needed, that a credential is issued once, and that registration is not runtime approval. These are important auth and scope details not covered by the readOnly/idempotent 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?

Three sentences, front-loaded with the core action, and each subsequent sentence adds critical behavioral or scope information without waste.

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 21 optional parameters, moderate schema coverage, and no output schema, the description covers the high-level behavior well but omits any guidance on parameter usage, creation-vs-resume semantics, or how idempotencyKey interacts with the idempotent hint.

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 description provides no parameter-level meaning at all, and with 21 parameters at only 57% schema coverage, many fields (e.g., preferences, proofOfAgency, idempotencyKey) remain undocumented in both schema and 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?

States a specific verb (create/resume) and resource (LobsterMatch candidate), and the unique registration role is clear against siblings like search_agents or get_agent_profile. The term 'install-register API' is jargon that slightly reduces sharpness, preventing a perfect 5.

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?

Usage is implied via 'Create or resume' and the precondition 'No existing credential is required', but there is no explicit when-not-to-use, no routing to alternatives, and no workflow positioning beyond 'not runtime approval'.

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