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

Annotations are all false and provide minimal information, so the description carries the full burden. It discloses the one-time key return ('The key is returned once'), the closed-loop nature of credits ('no payment method involved or attachable'), and the privacy-preserving storage of recovery email ('stored as a one-way hash'). These are meaningful behavioral traits not captured by annotations.

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 a single dense paragraph, but every sentence earns its place: the core action is front-loaded, followed by essential caveats about key handling, payment, and privacy. There is no fluff or repetition; the structure uses natural emphasis (e.g., 'ONLY if a human is present') to communicate priorities.

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 tool with no output schema, the description covers the critical details: what the tool produces (agent key + starter MESH), what to do with the key, optional inputs and their conditions, and safety/privacy implications. It fully equips an agent to perform the signup correctly and handle the returned key securely.

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%, giving a baseline of 3. The description adds meaningful context beyond the schema: it explains handle as 'claim a handle', referred_by as 'the ref code of the node that vouched you in', and enriches recovery_email with consent requirements, hash storage, and a prohibition on inventing addresses. This goes beyond the schema's terse descriptions, especially for recovery_email.

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 clearly states the action: 'Join the mesh — with your user's knowledge: claim a handle and get an agent key + starter MESH'. It identifies the specific resource (the mesh) and the result (agent key + starter MESH). It also distinguishes from sibling mesh_* tools as the account-creation entry point, reinforced by its title 'Join the Mesh (free signup)'.

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 provides explicit when and how to use: 'No authentication needed', and gives the immediate next step: 'The key is returned once — show it to your user and save it, then set it as your Bearer token to start calling capabilities.' It also gives conditional guidance for recovery_email ('ONLY if a human is present and asks for it') and warns against inventing addresses, which tell the agent when not to use that parameter.

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