Get Server Capabilities

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description goes beyond them by disclosing the exact payload contents (range/coordinate semantics, error codes, limits, data pin, license, citation) and by stating what the 'full' mode adds — genuinely useful behavioral context for a tool with no output schema.

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 payload contents are front-loaded in a single dense clause and the detail behavior follows immediately, so an agent reads the important part first. The trailing 'Signature: get_server_capabilities(detail=)' restates the name and schema and earns nothing, and 'strchive-link' is unexplained product jargon.

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 one optional enum parameter, no output schema, and a simple read operation, the main burden is describing what comes back — and the description does that item by item. Nothing an agent needs in order to call it correctly is missing, though a note on response size or when to prefer summary over full would close the last gap.

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% and the enum already documents both 'summary' and 'full' with the default. The description only restates that detail='full' adds usage notes, which is essentially a duplicate of the schema text — baseline 3 is correct when the schema carries the parameter semantics.

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 verb and resource ('Return the ... discovery surface') and enumerates exactly what that surface contains: tool signatures, aliases, response modes, coordinate semantics, error codes, limits, data pin, license, citation. That is clearly distinct from siblings like get_locus or search_loci, though it never explicitly contrasts itself with get_diagnostics, which is the nearest conceptual neighbor.

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?

Usage is implied (this is a bootstrap/discovery call to learn the API surface) and the detail parameter's effect is stated, but there is no explicit 'call this first / call this instead of get_diagnostics' guidance and no stated preconditions. An agent can infer the when-to-use from the word 'discovery surface' but must do the inferring itself.

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