Get task-scoped brand context

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: deterministic fixed-table mapping, no inference, and explicit no-match reporting rather than guessing — which tells the agent how to interpret a thin result. It loses a point only because it recaps the return fields (context, output_contract, matched_selectors, no_governed_match) that the output schema already declares.

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 core purpose and the primary routing instruction, and the NOT-clause closes it well. The middle is dense — four example trigger phrases plus a determinism paragraph — so it is slightly longer than needed, but every sentence carries routing or behavioral information.

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 read-only 4-parameter selector with a full output schema, this covers everything an agent needs: what it returns, what determinism guarantees, how misses surface, and which sibling to use instead. No gap remains that would cause a wrong call.

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. The description adds real meaning on top: it explains that task_type drives selection via a fixed table with visual-vs-copy-vs-mixed routing, and that audience matching is normalized-substring against governed persona names with an explicit no-match. It does not further explain budget or channel beyond the schema.

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 ("select a task-scoped brand context from the compiled runtime") and immediately contrasts it with the two siblings that do something else (brand_runtime for the full runtime, brand_check for auditing finished content). An agent can distinguish this from all 11 siblings without opening a 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 trigger phrases ("write this in our voice", "build a landing page") plus a clear negative clause naming the alternatives: "NOT for reading the entire runtime (use brand_runtime) or checking finished content (use brand_check)". When-to-use and when-not-to-use are both present.

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