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

Annotations declare readOnlyHint=true, and the description reconciles the apparent 'propose' verb with that by stating 'This does not execute anything' and that the founder enters data and approves in the native app. It also adds the re-read-before-claiming-success protocol and the no-secrets constraint, which annotations alone would not convey. It stops short of saying what happens when the gating condition is not met or how the proposal surfaces, so a 4 rather than 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?

Purpose and the gating condition come first, and every sentence carries information: constraints, non-execution semantics, per-kind parameter routing, and sibling routing. The conditional parameter rules are a dense run-on that could be bulleted, but nothing is filler.

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?

For a complex, enum-driven tool with five optional nested fields and only one required top-level parameter, the description supplies the gating logic, the safe-input contract, the human-approval model, and which IDs each action kind needs. Return values are covered by the output schema and safety by the annotations, so the remaining gaps (firmCode, failure mode) are minor.

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 description coverage is 0%, so the description must carry the load, and it does: it maps action kinds to required fields (company_id except pre-company founder/shareholder actions, domain actions take domain, application/MONEY_RECEIVE take resource_id, SIGNATURE_SEND takes resource_ref, child tax actions take subject_id). The 'firmCode' parameter is never mentioned and the casing differs from the schema ('company_id' vs 'companyId'), leaving one real gap.

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 ('proposes a native Mac secure action sheet or confirmation card') plus the gating condition ('when the chat context advertises native secure action support'). It also names what it is not ('Transfers are not a native action'), so an agent can separate it from the transfer siblings without opening a 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 explicit preconditions (context must advertise native support), explicit exclusions (transfers must go through the transfer tools: draft, phone approval, commit), and a negative instruction ('Never call raw sensitive setters or request a value in chat'). The alternatives are named rather than implied.

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