describe_capabilities

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses a key behavioral trait: unsupported verbs will be refused, and it explicitly states what the tool never returns (anchor ids). The verb 'List' implies read-only behavior, though it does not explicitly say 'no side effects'. This is solid disclosure for a no-argument introspection tool.

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 sentences, all information-dense with no filler. The primary action and timing ('before planning an edit') are front-loaded, and each subsequent clause adds distinct value. Slightly long, but every sentence justifies 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?

There is no output schema, so the description must explain what the tool returns—and it does: contract version, formats with verbs/change modes, host ceilings, and connections with capabilities. It also covers error behavior (refusal) and the boundary of what is not returned (anchor ids). For a zero-parameter introspection tool, this is complete.

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 tool takes zero parameters, so the baseline is 4. The description does not need to clarify parameter meaning, and it instead uses the space to describe what the return payload will contain, which is the most relevant semantic guidance for a no-arg tool.

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 clear verb 'List' and specifies exactly what is listed: contract version, formats with plan verbs/change modes, host ceilings, and connections with held capabilities. It also distinguishes itself from inspect_document by explicitly stating that anchor ids are never listed and where they come from, which differentiates it from siblings.

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 gives a clear when-to-use context: 'before planning an edit', which tells the agent this is an up-front introspection step. It also provides an exclusion and alternative by telling the agent that anchor ids come from inspect_document, effectively routing away from this tool for that need. It stops short of explicitly naming sibling tools as alternatives for other cases, so a 4 is appropriate.

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