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

Annotations already indicate mutation (readOnlyHint=false) but the description adds substantial detail: it's billed, has no fixed entity-count cap but live quotas can stop it, each entity must pass all models for fusion/admission, and confident mismatches skip without pausing the batch. This goes well beyond the annotations and is highly useful.

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 dense but well-structured, leading with the core action and constraints, then returns, caveats, workflow, and sibling differentiation. Every sentence adds value, though it is on the longer side. Given the complexity (9 params, async behavior), this length is justified.

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 tool with this complexity, the description covers billing, async behavior, failure modes, model selection, workflow, attachments, differences from the sibling, and points to docs for detailed contracts. The output schema likely covers the return shape (job_id, total), so nothing critical 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. The description adds meaningful context beyond schema fields: the model auto-selection logic ('pinned per-task default... else best blended benchmark score'), the classification_model behavior ('Confident mismatches skip that entity; softer verdicts become prompt context'), and the one-of constraint reiterated. It also clarifies attachments apply to every entity. This elevates it to a 4.

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 description opens with a specific verb and resource: 'Start billed asynchronous enrichment of an entity list' and immediately constrains it to 'exactly one of schema_id or target_schema', which clearly distinguishes it from the single-entity enrich_entity sibling. It also states the return values (job_id and total) and the workflow (poll get_job_status then list_records).

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?

Explicitly contrasts with enrich_entity ('Unlike enrich_entity, this tool exposes neither database_sync=false nor web-search activation') and gives a post-call workflow ('Poll get_job_status, then list_records(job_id=...).'). It also references documentation for input contracts and recovery, leaving no doubt about when to use it.

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