sign_in

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

With no annotations, the description carries the full burden and does well: it discloses that a key is created, where it is written on disk, that it is reused from now on, that the password is single-use and not stored, and that the key must never be echoed back. It omits failure behavior and what happens if credentials already exist (overwrite vs error).

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 consequence in the first sentence, then layers scope guidance and the secrecy constraint. The sentences are long and run together (line-broken mid-phrase), and the trailing 'never repeat the key back' reads as a tacked-on instruction rather than an integrated caveat.

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?

An output schema exists, so return values need no explanation, and the description covers the mutation, its persistent side effect, credential storage, and the scope decision. What remains thin is the preconditions/edge cases: behavior when already signed in, and whether the new key invalidates prior keys.

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 0%, so the description must compensate and largely does: username is clarified to allow email, password is marked single-use, and scope is given meaning ('read or control') and a decision rule that the schema does not express. key_name is never mentioned, leaving one of four parameters undocumented anywhere.

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 and resource: authenticates an existing Aivy account and mints an API key persisted to ~/.aivy/credentials.json. The phrase 'existing Aivy account' plus 'Needs no existing key' implicitly separates it from register_account/verify_registration, but no sibling is named outright, so differentiation is inferred rather than stated.

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 real selection context: this is for accounts that already exist, requires no prior key, and 'control only if the person asked' constrains scope escalation. It never explicitly says 'if the user has no account, use register_account instead,' so the exclusion is implied rather than spelled out.

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