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

With no annotations provided, the description carries the full burden. It discloses two important behavioral constraints: bit scores below 50 are not reported and results are truncated to the top 50 per protein. It also mandates reporting species names with taxon IDs, which sets expectations for output. However, it does not explicitly state the operation is read-only or mention any API/authentication requirements.

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 front-loaded with the main purpose and then uses bullet points for scannable behavioral details. Every line adds value—no filler, rhetorical fluff, or redundant restatements of the title. It's tight but complete.

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 covers the essential usage contexts (intra-species vs cross-species), output filters (bit score threshold, top-50 truncation), and reporting expectations. The presence of an output schema helps with return-value details. The main gap is the missing explanation of the 'species' parameter, which prevents full self-sufficiency.

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 description clarifies the role of species_b (optional, intra-species when omitted) but does not explain the 'species' parameter or the encoding format for 'proteins'. Given the low schema description coverage (33%), the description should compensate by explaining parameter meanings, but it leaves one parameter unaddressed and repeats only what the schema already says for another.

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 opens with a specific verb and resource: 'Retrieves pairwise protein similarity scores (Smith–Waterman bit scores) for the query proteins.' It clearly differentiates from sibling tools by focusing on homology across specified target species, matching the title's promise.

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?

It clearly states when to use the tool (to retrieve homologs) and the key branching condition: no species_b means intra-species, while specifying taxon IDs enables cross-species/clade searches. It also advises asking the user to clarify multiple target species, but doesn't name alternative tools or explicitly exclude their use.

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