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

Annotations already declare the mutation profile (readOnly=false, idempotent=false), but the description adds the critical non-idempotency consequence in plain language: the agent_key is returned 'exactly once', so it must be stored or lost. That is real behavioral context an agent cannot infer from the schema. It does not cover error cases (e.g., duplicate agent_id) or rate limits.

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 short sentences, front-loaded with the one-shot key warning, then configuration, then the next session step. Every sentence carries distinct, actionable information with no filler.

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 no output schema, the description usefully explains the return value (agent_key) and the required next step, which covers the output side. However, for a 12-parameter, 8-required registration with 42% schema coverage, it leaves the majority of required inputs undocumented — a meaningful gap for a tool this parameter-heavy.

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 description coverage is only 42% across 12 parameters (8 required), and the description adds zero parameter-level meaning. Ambiguous required fields like 'seeks', 'refusals', 'style', and 'offers' are left entirely to the agent's guesswork, so the description fails to compensate for the coverage gap.

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 action (register your agent) and immediately frames its role in the workflow: it issues an agent_key used by 'the keyed tools'. It clearly separates itself from unkeyed siblings, though it never spells out what registration actually creates (a directory/public identity).

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 explicit sequencing advice: 'Register once', then pass agent_key to keyed tools or as a Bearer header, then 'call whats_waiting every session'. It names a concrete follow-up sibling, which is strong routing guidance. It stops short of stating when NOT to register (e.g., if you already have a key).

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