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

Annotations are sparse (readOnlyHint=false, destructiveHint=false, no idempotency), so the description carries the burden — and it delivers: long-running tools return a job_id requiring polling, a brain_context gate that errors without prior brain_query, and a gateway that resolves/merges image composition inputs into a single image_urls array. The only unstated behavior is the general return shape of normal (non-async) calls, which varies by target tool.

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?

The description is long (~250 words) but every sentence carries distinct operational information, and key warnings are front-loaded and labeled (IMPORTANT, BRAIN). The purpose sentence opens the text, and routing guidance precedes edge cases. The length is justified by the tool's complexity as a dispatcher, though it could be tightened slightly.

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 dispatcher with 7 parameters, a nested backend object, ~50 siblings, and no output schema, the description covers the hard parts: choice vs route/discover, built-in exclusion, async job flow, image-URL preparation, and the brain gate. A general normal-result description is absent, but return shapes are inherently tool-dependent for a dispatch layer, and the description names the one universal async return (job_id).

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 description coverage is 100%, so the baseline is 3; the schema's input-parameter description is already exceptionally rich (persona_file_id, scene_file_id, style_reference variants, image-composition merging). The tool description itself adds workflow context — file_write before passing URLs and brain_query before brain_context — but does not meaningfully extend parameter semantics beyond what the schema already states.

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?

The opening sentence names a specific verb and resource — 'Call a ToolRouter catalogue tool' — and immediately differentiates from siblings: route is for natural-language intent, discover is for schemas/listing, and built-ins like credits_balance are explicitly excluded ('call them directly, never through use_tool'). An agent can tell exactly what this tool is for and what it is not.

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?

The description gives an explicit decision tree: prefer route when the tool/skill is unknown; use discover to get schemas then pass exact names here; never route built-ins through this tool; poll long-running jobs with job_get; use file_write first for local images; consult brain_query when a brain_context error occurs. This is exemplary when/when-not guidance with named alternatives and conditions.

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