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

Goes far past the annotations (destructiveHint=true, idempotentHint=false) by disclosing the re-read side effect, the cross-app daily-cap accounting, the first-brief lock, and precisely what a duplicate idempotency_key does — returns the first answer, starts no second job, spends no allowance. The key-based retry semantics reconcile with idempotentHint=false rather than contradicting it: idempotency is caller-supplied, not intrinsic.

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?

Front-loaded with the action and its side effect, then a series of short constraint sentences that each carry distinct information. It is staccato and runs long, but no sentence is filler and nothing important is buried.

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?

A destructive, quota-consuming mutation with a mandatory idempotency key, fully covered: mutation semantics, partial-update behaviour, preconditions, lock state, and retry behaviour are all stated. An output schema exists, so omitting return-value detail is appropriate.

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 100%, so the baseline is 3, but the description earns above it with "Only the dimensions you send change; an empty list clears one" — PATCH-style partial-update versus clear semantics that the schema's bare array descriptions do not convey. The idempotency_key advice duplicates the schema text rather than adding to it.

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?

"Sets the ideal customer profile" is a specific verb+resource, and the added clause about re-reading competitor overlap captures a side effect that no other sibling has. It is distinguishable from update_company_profile/get_company_profile by resource name, though it never explicitly routes the agent away from those neighbours.

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 unusually concrete when-not conditions: admin-only, requires a paid plan or the free first week, blocked while the first brief is running, and consumes a shared per-workspace daily cap. An agent can decide before calling whether it is permitted to act, which is exactly what this dimension demands.

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