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

Annotations declare the mutation profile (readOnlyHint false, idempotentHint false, destructiveHint false), and the description adds substantial non-obvious behavior beyond them: keys never expire, repeated calls mint a new key rather than reusing one, keys carry per-key rate limits, and usage/referrals are tracked per key with a privacy-policy link. That is exactly the context an agent needs before treating the key as durable state.

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-loaded with the core action, then behavior, then the optional parameters and support contact. Slightly long and the privacy-policy URL is parenthetical, but each sentence carries actionable information and nothing is padded.

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?

With an output schema present, the return payload need not be described. The description covers provenance, lifecycle (non-expiring, re-issuable), rate-limit implications, parameter constraints, and an escalation route, leaving no material gap for calling the tool correctly.

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 the two optional params are already documented, but the description still adds meaning the schema does not: the labels are metadata only, do not affect rate limits or capabilities, and should not contain personal data. It corroborates rather than merely repeats 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 states a specific verb and resource ('issues a free anonymous key for Blue Pillow Hotels & Stays') and immediately distinguishes it from all siblings by noting they consume the key via their `api_key` argument. An agent can tell this is the entry-point credential tool without opening any other schema.

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?

It gives clear context on when this is needed (no account/sign-up, key feeds the other tools' api_key), and clarifies the repeat-call case ('calling this tool again issues a new one') plus the escalation path (email for higher limits). It stops short of an explicit 'call this before search_stays/get_property_details' ordering instruction, so it is clear but not fully prescriptive.

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