inspect_locus

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

Annotations declare readOnlyHint=true and openWorldHint=true, so the description does not need to restate those. However, the description adds a critical behavioral note: 'Not implemented in this build: returns error code unsupported (E9)'. This is valuable transparency. But it also mentions a privacy condition about external annotation, which is useful but vague. The description does not explain what constitutes 'external sources' or the exact scope of the unsupported feature.

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 concise, consisting of two sentences. The first sentence states the purpose and the privacy condition. The second sentence reveals the unsupported status. The text is front-loaded with the core function, and the critical limitation is provided early. There is no fluff, so every sentence earns its place.

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 output schema exists, so return value details are not required. However, the description is incomplete for a complex tool with 6 parameters. It fails to mention how parameters like files, interval, max_records interact, or what 'public evidence' means. The unsupported status is a major caveat but is not fully contextualized. The lack of usage guidance and parameter semantics leaves an agent guessing about how to construct a valid request.

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 only 33%, so the description must compensate for parameters not documented in the schema. The description mentions allow_external_annotation, which adds meaning beyond the schema's boolean field. However, it does not explain the other parameters like files, interval, reference, max_records, or reference_sources. The interval and files parameters likely have clear semantics from their type definitions, but the description does not help an agent understand how to populate them for this tool. Thus, it partially compensates but leaves gaps.

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 states the verb 'Combine' and the resource 'data from several files at one locus', which gives a clear overall purpose. However, it does not differentiate this tool from siblings like get_reads, get_variants, or get_features, which also return data at a locus. The phrase 'plus public evidence' hints at combining external data, but it's not explicit enough to distinguish it clearly.

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?

There is no guidance on when to use this tool versus alternatives. The description does not mention any conditions, prerequisites, or alternative tools. An agent would not know whether to prefer inspect_locus over get_reads or get_variants for a given task.

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