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

Goes well beyond the annotations: it discloses that the operation is free, takes 1-3 minutes, that each polling call blocks up to 20 seconds, and — critically — that reading again replaces the existing profile. That last point gives concrete meaning to destructiveHint=true rather than merely restating it.

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-loads what the tool does, then the start/poll/finish sequence, then the guardrail on re-reading. Three short blocks, no filler, and the workflow order matches the order an agent executes it.

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?

An output schema exists so return values need no explanation, and the description still supplies the multi-call lifecycle, latency expectations, cost, and the handoff to brand_profile. Nothing an agent needs in order to call this correctly is missing.

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 adds mode semantics the schema does not: 'url' starts a job and 'jobId' (passed alone) polls an existing one. The only minor gap is that it does not state what happens if both or neither are supplied.

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 ('Read a brand from its website and save it as the brand profile') and enumerates exactly what the profile contains (name, logo, colours, voice, products, audiences, competitors, market white space). It also implicitly separates itself from brand_profile by naming that sibling as the consumer of results.

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 when-to-use conditions ('only when the user asks or when brand_profile has nothing') and an explicit workflow: start with url, poll with only jobId, then call brand_profile when status is done. Alternatives and sequencing are fully spelled out.

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