Submit a website form

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action (submit values), the encoding, and the return (HTTP status and snippet). However, it does not disclose potential side effects (e.g., submitting data could mutate server state) or mention authorization, rate limiting, or failure behavior. The clause 'real website form' hints at an actual external action, but more explicit disclosure would be safer for an agent. The constraint on when to call it is a good behavioral trait.

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 sentence that front-loads the purpose and includes the usage constraint and return format. It is concise with no filler. The critical usage condition is placed early, making it easy for an agent to parse. Slightly more structure (e.g., separating the return statement) could improve readability, but as is, it is efficient.

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?

The tool has four parameters, two of which are nested objects, and no output schema, so the description must cover operational context. It states what it does, when to call it, and what it returns. However, it lacks guidance on error handling, side effects, or details about the structure of 'fields' and 'headers' beyond schema descriptions. Given the absence of annotations, an agent would benefit from explicit notes about the potential mutating nature of submitting a form. It is adequate but not comprehensive.

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?

The schema provides descriptions for 'action' and 'fields' but not for 'method' or 'headers' (50% coverage). The description adds 'form-encoded GET or POST,' which clarifies the method parameter's purpose and its encoding format. However, it does not add meaning for 'headers' or provide additional detail on how 'fields' should be structured beyond the schema. Since the schema already documents half the parameters and the description clarifies method encoding, it meets the baseline but does not fully compensate for the undocumented parameters.

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 verb 'Submit' and the resource 'a real website form,' and specifies the encoding ('form-encoded GET or POST'). It distinguishes itself from the sibling card-creation tools by emphasizing this is an actual submission, and the reference to 'mirrored form card' implicitly connects it to mirror_web_form. Specific and unambiguous.

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 gives a clear condition for use: 'Only call this with data the user entered in a mirrored form card, or values the user explicitly confirmed.' This provides a strong guardrail. It doesn't explicitly name alternatives or say when not to use it, but the constraint implies it should be used only after mirror_web_form and with user consent. Evidence: 'Only call this...'.

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