architect_capabilities

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered. The description adds only the notion that results include authority boundaries and coverage, which is modest extra context; it says nothing about output shape or size, which annotations cannot convey.

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?

A single front-loaded sentence with no waste. It is perhaps too compressed — 'coverage' of what is never unpacked — but it is not padded or back-loaded.

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 carries the burden of explaining what comes back, and it offers only a rough list of categories ('host actions, coverage, authority boundaries'). That is directionally adequate for a parameterless read tool, but an agent still cannot anticipate the return structure or how to interpret 'coverage'.

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 of 4 applies and there is nothing for the description to compensate for. The empty schema is consistent with a parameterless introspection call.

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 verb 'Read' and the objects 'supported host actions, coverage and authority boundaries' are present, so the general intent is a capability/introspection dump. But 'coverage' and 'authority boundaries' are abstract, and nothing distinguishes this from sibling introspection tools like architect_doctor or architect_console_url, leaving the agent to infer the exact scope.

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 statement of when to call this versus the many architect_* siblings, no prerequisites, and no exclusions. An agent can guess it is a discovery call, but the description never says so explicitly or points at alternatives.

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