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

The description explicitly states 'Idempotent,' but the annotations declare idempotentHint: false. This is a direct contradiction. The description also claims it writes a field and does not open a PDF, which are transparent disclosures, but the idempotency conflict is a serious misalignment that undermines trust in the entire behavioral description.

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 extremely verbose, consisting of several long paragraphs with repeated emphasis (e.g., 'step one', 'step two' mentioned multiple times). While it is well-structured and front-loaded with the core purpose, it over-explains and could be significantly tightened without losing essential information. The unwieldy length detracts from readability.

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 description covers many operational details: preconditions, error handling, scope, and return values. However, the idempotency contradiction introduces misleading information that could cause an agent to retry when it shouldn't, which is a critical gap in correctness. While most necessary context is present, the false claim undermines completeness.

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 only parameter, eid, is mentioned only as 'Args: { eid? }' with no explanation of what it represents. Schema coverage is 0%, so the description must compensate, but it does not clarify that eid is likely the event identifier. While the context of 'this event's roster' implies it, the tool definition fails to explicitly define the parameter, leaving room for misinterpretation.

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 tool's purpose: 'Record that you have signed the venue's NDA.' It goes further to distinguish this step from the email NDA signing, explicitly framing it as 'step two' that writes the nda_signed_at field. This is specific, unambiguous, and differentiates it from related actions.

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-to-use guidance: it is step two after signing the emailed NDA, and it is only valid for roster members. It also states when NOT to use it (if not on roster, get a seat first via ic_hack_apply or an organizer) and names related tools (ic_hack_me, ic_hack_checkin). This leaves no ambiguity about the correct context.

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