Compare methods

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

No annotations exist, so the description carries the full behavioral burden. It discloses one genuinely useful boundary — the tool reports verified overlap and explicitly does not infer benchmark equivalence — which shapes downstream agent reasoning. It leaves the read-only status, rate or volume behavior, and zero-overlap handling undisclosed, so the disclosure is partial.

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?

One sentence with the verb front-loaded and every clause earning its place: inputs ('two bounded method searches'), output ('verified paper overlap'), and a scope boundary ('without inferring benchmark equivalence'). There is no filler, repetition, or schema echo.

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?

With no output schema, the description must convey the return shape, and 'report verified paper overlap' only hints at it — an agent cannot tell whether the result is a list of paper identifiers, a count, or detailed records. The ambiguous 'bounded' qualifier and the unexplained limit parameter add further gaps that nothing else in the definition fills, since there are no annotations and no schema descriptions.

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 maps the two required string arguments to 'two bounded method searches,' which orients the agent, but it never states what makes a search 'bounded,' how that relates to the limit parameter, or what limit (default 10, max 50) actually controls. The compensation is partial at best and leaves the limit parameter's meaning to inference.

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 names a specific action ('Compare'), a specific resource ('two bounded method searches'), and a specific output ('verified paper overlap'). It differentiates from siblings like compare_papers and compare_paper_to_code by scoping to method-search results, and the closing qualifier 'without inferring benchmark equivalence' further disambiguates what the tool does not claim. An agent can tell this apart from its comparison siblings without reading their schemas.

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 intended use case is implied: call this when you have two bounded method searches and want to know their paper overlap. However, no alternative tools are named and there is no when-not guidance, which matters because compare_papers and compare_paper_to_code create real routing ambiguity among siblings. The 'without inferring benchmark equivalence' clause is the closest thing to an exclusion, but it is framed as a scope statement rather than usage guidance.

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