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

With no annotations, the description bears the full burden of behavioral transparency. It adds some useful traits—source-bounded results, explicit missing facts, and a 0.008 USDC cost—but it does not disclose read/write behavior, whether it fetches the source URLs, persistence, auth, response shape, or failure semantics.

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 definition is compact and front-loaded: scope appears first, missing-facts behavior second, and price last. There is no filler and each clause earns its place. It is under-specified overall, but the structural efficiency is strong.

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?

Given three parameters, a nested subject object, no output schema, and a crowded sibling list, the one-sentence description is insufficient. The agent cannot learn how evidence is returned, how subject relates to expected_fields, or when to select this tool over similar ones.

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?

The schema has 0% description coverage for three parameters, so the description must compensate. It indirectly maps 'source-bounded' to source_urls, 'entity' to subject, and 'field coverage ... missing facts' to expected_fields, adding some meaning beyond the bare schema names. However, it does not explain formats, requiredness, constraints, or how subject and expected_fields interact.

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 conveys a specific output concept—'Source-bounded entity field coverage with explicit missing facts'—and mentions the price, but it uses a noun phrase rather than a clear verb+resource statement. It does not distinguish this from siblings like multi_source_fact_bundle or source_backed_search.

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?

There is no when-to-use guidance, no exclusions, and no reference to alternatives. The description only characterizes the result and cost, leaving the agent to infer when this evidence tool should be chosen over the many related tools in the sibling list.

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