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

Annotations only state readOnlyHint=false and destructiveHint=false; the description adds real value beyond them by disclosing the consent/auth prerequisite, idempotency/retry guidance, and the canonicality rule about trusting actual_tool_output rather than issuing a state-recovery call. The 'confirmation boundary' paragraph is generic template text that mostly restates safety defaults rather than tool-specific behavior, keeping it from a 5.

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 critical consent condition is front-loaded in sentence one, which is good. However, the closing block of canonicality/idempotency/confirmation-boundary text is generic boilerplate, and 'every prerequisite stated above' is a dangling reference to context that is not present. Several sentences do not earn their place.

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?

There is no output schema, and this is a legally consequential mutation, so the description must carry the load. It covers auth, consent, idempotency, and the canonicality escape hatch, which is substantial, but says nothing about the outcome of a successful sign/decline or irreversible state change, and the 'prerequisite stated above' phrase leaves the actual prerequisite chain ambiguous.

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% and there are 7 parameters (6 required), so the description must compensate. It does map meaningfully onto documentHash (exact frozen PDF), signatureName (full legal name), decision (sign/decline), and consentId (fresh explicit consent), but gives no format, syntax, or role detail for companyId or the _corply_context object. Partial compensation over an undocumented schema.

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 states a concrete verb+resource: record the recipient's own electronic signature or decline for a governed/company-action document, and names the mechanism (PDF hash, full legal name, fresh consent). It is clearly distinct from the many read/list siblings and from request_governed_signatures. It stops short of naming the closest alternative tools (e.g. sign_bundle) explicitly.

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?

Strong explicit preconditions: only after the recipient has read the exact frozen PDF and given fresh explicit consent in their own words in this chat. It also gives a clear prohibition: never sign for another person or infer consent from a link click. No alternative-tool routing is offered, so it falls short of a 5.

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