get_capabilities

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

Annotations already declare this a safe, idempotent, non-destructive, closed-world read, and an output schema exists, so return structure needs no prose. The description adds that the result covers registered operations, models and implementation boundaries — useful scope context, but nothing about completeness guarantees, size, or caching behavior.

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 sentence with no filler and the scope stated up front. It is slightly compressed — 'implementation boundary' is undefined and the reader must infer what a capability record contains.

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 zero parameters, full annotation coverage, and a dedicated output schema, the description only needs to convey scope and it does. A short note that this is the entry-point for discovering the rest of the tool surface would make it 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 per the baseline there is no parameter meaning for the description to carry. Nothing in the description misleads about inputs.

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 gives a specific verb ('Discover') plus an enumerated resource set (operations, workflows, input schemas, models, implementation boundaries), which distinguishes it as a global introspection tool versus narrower siblings like get_workflow or get_input_schema. The phrase 'implementation boundary' is vague, but the overall intent is clear.

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 only implied — an agent can infer this is a discovery/onboarding call, but the description never says when to prefer it over get_workflow, get_input_schema or get_workspace_state, nor does it say to call it first before other tools. No explicit exclusions or alternatives are named.

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