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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false; the description adds real context beyond them: it is non-destructive by construction (only empty fields are touched), it is admin-only, and it consumes a per-workspace daily quota. It does not explain the retry/idempotency-key behavior that pairs with idempotentHint=false, leaving a small gap.

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, each carrying distinct information: what is drafted, the non-destructive constraint, the read-back tool, the permission requirement, and the quota. Nothing is redundant and the core action is front-loaded.

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 is a single-parameter, non-destructive generator with an output schema that covers the return value, so the description need not explain results. Permissions, cost (daily cap), scope of mutation, and the follow-up read tool are all covered, which is everything an agent needs to call it correctly.

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?

There is only one parameter and the schema documents it at 100% coverage, including what the key is for and how retries behave, so the description adds no parameter-level meaning. With schema doing the work for a single well-documented parameter, the baseline of 3 is appropriate.

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 (drafts) plus the exact resource and the three fields it fills (value propositions, differentiators, exclusions), and names the source it reads from (the company's own website). This clearly separates it from siblings like update_company_profile and update_icp, which set fields directly rather than generating them.

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?

Explains the fill-only condition ('Filled fields stay as they are') and routes the agent to get_company_profile for reading the result, so the use/read split is explicit. It does not state the inverse case (e.g., use update_company_profile when you want to write a field manually), so it falls just short of full when/when-not guidance.

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