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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial behavior: unreported fields come back as 'not present' rather than estimated, a freshness warning fires when evidence ages differ by more than two days, and unowned ids surface in missing[]. These are non-obvious traits an agent could not infer from structure.

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 action and scope, then a tight sequence of constraints; essentially every sentence carries distinct information. It runs long enough that a couple of clauses (e.g., the enumerated facet list) could be trimmed, keeping it just short of a 5.

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 prose. Against that, the description covers input bounds, ownership failure handling, evidence-freshness caveats, and the sequencing context, leaving nothing an agent needs to call it correctly.

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?

With 100% schema coverage the schema already documents saved_ids, its 2-4 bounds, and the id pattern, so baseline is 3. The description adds meaning beyond the schema by clarifying what happens to ids the user does not own (they land in missing[]), covering the failure case the schema cannot express.

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 (compare), resource (2-4 saved analyze_product results), and scope (side by side using only stored evidence) with the exact facets compared. An agent can distinguish it from analyze_product and list_saved_research without opening any 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?

Explicitly sequences the tool ('Use after list_saved_research') and gives the triggering user intent ('which of their saved products to pursue'). It also rules out fresh analysis, but never names the sibling an agent should reach for instead when the user wants new analysis, so it stops short of full when-not/alternative coverage.

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