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

Annotations cover only the safety/idempotency profile, and the description adds substantial behavior the annotations cannot express: async jobId handoff, the 20s timeout, SSRF/private-URL blocking, non-2xx and non-HTML handling, and the critical non-obvious trait that failures degrade to EMPTY token arrays as a succeeded job rather than erroring. This is exactly the kind of disclosure that prevents an agent from misreading an empty result as a bug.

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 ASYNC contract, and essentially every clause carries operational information (jobId, wait_job kind, degradation behavior, fallback). It is dense with nested parentheticals and em-dashes in a single paragraph, which slightly impairs scanability, but there is no filler to cut.

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?

Complete for an async, single-parameter, output-schema-backed tool: the description supplies the job lifecycle, the wait_job continuation, the persistence gap and its remedy, plus failure semantics that the output schema alone would not disambiguate. Nothing an agent needs to call or correctly interpret this tool 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% for the single url parameter, so the baseline is 3, but the description adds real semantic constraints beyond 'format: uri': the URL must serve server-rendered HTML/CSS, and JS-rendered SPAs will typically yield empty output. That materially changes how an agent should pick and interpret the value.

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 precise verb+resource ('queue brand-token extraction from a website URL') and immediately scopes what is produced (colors/fonts/title/description) and how (HTML/CSS regex parse, not vision). It also names the two sibling touchpoints, wait_job and create_brand_kit, so an agent can route without opening either 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 sequencing ('returns a jobId immediately; then wait_job(kind="brand_kit_extract", id=jobId)'), an explicit exclusion ('NOT a screenshot/vision pass'), a persistence boundary ('does NOT persist — review the tokens, then call create_brand_kit'), and a fallback path for JS-rendered SPAs. When-to-use, when-not-to-use, and the alternative are all covered.

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