compare_research_evidence

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

With no annotations available, the description carries the full behavioral burden and does so excellently. It explicitly discloses that missing values never match, and that the tool does not read files, authenticate hashes, execute code, persist records, or certify compatibility, calibration, unused OOS, or candidate eligibility. This is unusually transparent and prevents false assumptions about side effects and guarantees.

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?

Three tightly packed sentences with no filler. The main action and resource are front-loaded, what it reports follows immediately, and the non-behaviors are listed compactly. Every sentence earns its place and the structure makes the tool's boundaries easy to scan.

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 no output schema and no annotations, the description does a strong job: it covers the input kind, the comparison axes, the report contents, and important caveats. It could add a bit more about the exact output shape or the meaning of 'unknown axes', but what is missing is minor given the schema already defines the input structure.

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 description coverage is 0%, so the description must compensate. It names the six compared axes (data, code, runner, candidate rule, parameters, environment) and clarifies that manifests are caller-supplied, but it does not explain how the 'previous' and 'current' objects map to the schema fields beyond enumeration. The 'Missing values never match' statement adds useful semantic, but the parameter semantics are only partially fleshed out.

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 ('Compare') and identifies the exact resource ('caller-supplied SHA-256 manifests for previous/current research data, code, runner, candidate rule, parameters and environment'). It also states what the tool reports ('changed and unknown axes plus required revalidation checks'), making it clearly distinguishable from sibling comparison tools like compare_strategy_experiments or compare_indicator_observations.

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 clearly implies when to use this tool: when comparing previous and current research manifests to identify changes and required revalidation. It does not explicitly name alternatives or exclusion conditions, but the context is strong and the negative boundaries ('Does not read files...') help an agent understand what this tool is not for.

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