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

With no annotations, the description carries the full burden and excels. It discloses that corroboration counts independent origins (echoes are collapsed), that counts are not truth, that no probability is the tool's own, and that the tool returns state='cannot-measure' with a reason instead of an empty list. These are non-obvious behaviors that prevent misinterpretation and false confidence.

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 but every sentence earns its place. It front-loads the core purpose, then systematically explains the meaning of the output fields, the counting logic, and the failure state. It is well-structured and avoids fluff, using precise phrasing that packs significant information into a readable paragraph.

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 there is no output schema, the description provides a thorough account of what the tool returns: claims, tier, independent origin count, origin names with wire marks, earliest report date, and entities. It also covers the edge case of unreadable data. This is unusually complete for a tool with no structured output schema, leaving little ambiguity for an agent.

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 input schema covers both parameters (tier, limit) with descriptions, so schema coverage is 100%. The description does not add extra semantic detail about how tier filtering behaves or how limit interacts with the results beyond what the schema already states. The baseline of 3 applies because the schema handles the parameters adequately.

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 clearly states the tool returns 'what independent sources agreed on' — a specific resource (corroboration layer) with a precise scope. It distinguishes this from raw event lists or truth by explicitly defining what corroboration means and what it does not mean (consensus vs verification). This is more than a simple verb+resource; it establishes the tool's unique semantic niche among the many get_* siblings.

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 implies usage context (e.g., when you need corroboration data rather than raw events or truth), and it warns about the limitations (not truth, not counting echoes). However, it never names an alternative tool or states explicit conditions for when to choose this over a sibling like get_events or get_truth_object. The 'when-not' is partially implied but not made actionable.

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