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

Goes well beyond the annotations: live submissions send a team notification and attempt CRM storage, and the idempotency contract (7-day reuse, never retry an uncertain action with a new key) is spelled out. This is consistent with idempotentHint=false, since the key is what makes retries safe rather than the tool being inherently idempotent.

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?

Five short sentences, front-loaded with the action and then the preconditions, safety mechanisms, and retry contract. Every sentence carries operational information with no 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 14-parameter mutation tool with no output schema, the description covers the critical unknowns: approval requirement, dryRun behavior, side effects, and retry safety. It does not describe what a dryRun or live response returns, but with no output schema that is a minor gap.

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?

With only 43% schema coverage across 14 parameters, the description compensates by explaining the semantics of the highest-risk fields: dryRun as a validate-only gate, confirmed as explicit person approval, and idempotencyKey as a retry-safety token. It adds meaning beyond the schema, though several required fields (name, role, stage, timeline, whatsapp) remain undocumented in both places.

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 ('Send a project idea to RegusciLabs to start discovery') and immediately scopes what it is not ('Does not subscribe the person'), which separates it from the sibling subscribe_pulse. An agent can identify the action and its boundary without opening the 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 concrete procedural guidance: validate with dryRun:true first, require explicit approval and contact details, and reuse the idempotencyKey for retries within 7 days. It distinguishes itself from subscribe_pulse, but it does not explicitly rank itself against read_information or search_information as alternatives.

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