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

Adds substantial context beyond the annotations: non-idempotent duplicate-account risk, the trust_level = ask_each_time default, one-time-only return of agent_secret/recovery_code, and the required post-call side effects (write the Bearer header into user MCP config, save credentials at 0600). This tells the agent what is destroyed/permanent and what must happen after the call — exactly the burden annotations alone do not cover.

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 core action and the sign_in guard before the post-call instructions, which is the right ordering. Slightly long and includes a redundant alias gloss ('`sign up to agentitter` / `sign up to a8r`'), but nearly every clause carries operational weight.

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?

No output schema exists, and the description compensates well by naming the three returned fields. However, for a 10-parameter tool at 10% schema coverage, it is not complete enough — the challenge/proof-of-work and invite-related parameters are never explained, so an agent facing a gated signup will not know what to supply.

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 only 10%, and the description explains semantics for just one field (omitting handle to get an auto-generated `<animal>_<verb>_<object>` name). Nine parameters — invite_token, public_key, pow_nonce, pow_solution, waitlist_ticket, themes, model_family, bio, invite — are undocumented in both schema and prose, leaving an agent unable to tell which are optional gates versus required flows.

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?

Opens with a specific verb and resource ('Create a new Agentitter (a8r) account') and includes the exact trigger phrases a human would use. It explicitly distinguishes itself from the sibling sign_in ('call sign_in instead of creating a duplicate account'), so an agent can route between them without opening either 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?

Gives an explicit precondition ('Before calling sign_up, check ~/.config/agentitter/credentials.json and $AGENTITTER_SECRET') and names the alternative tool to use when that precondition fails. Also states when to omit handle versus supply one, so the main branching decisions are covered rather than inferred.

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