get_evidence_packet

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

With no annotations provided, the description carries the behavioral burden. It does disclose a meaningful trait: the tool returns the 'smallest verified' packet, signaling minimization and verification. But it does not describe what happens when no question, claim, or entity is provided, what an evidence packet contains, or any operational constraints.

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?

A single front-loaded sentence communicates the tool's role and key behavioral promise with no wasted words. The main purpose is stated first, followed by the defining constraint.

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?

The description is adequate for a first-pass retrieval interface, but it lacks context around how this tool relates to the many siblings and how the optional parameters compose. Since there is no output schema, more detail about what an 'evidence packet' contains would help the agent invoke 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?

Schema coverage is 100%, so the schema already documents all four parameters. The description adds only the conceptual framing that the packet answers a question, but it does not deepen parameter meaning beyond what the input schema provides. Baseline 3 is appropriate.

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 uses a specific verb ('returns') plus a concrete resource ('smallest verified evidence packet') and condition ('sufficient to answer a question'). It clearly conveys what the tool does, and 'Primary AI agent retrieval interface' helps set it apart from the sibling search and verification tools, though it does not explicitly name a distinguishing alternative.

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?

'Primary AI agent retrieval interface' gives clear context that this should be the first retrieval tool an agent reaches for. However, it does not explicitly state when to use alternatives like find_evidence, verify_claim, or get_entity, nor does it state exclusions.

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