cap_edit_expert

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

With no annotations, the description discloses a non-trivial conversational workflow: initial load requires cap_id and empty message, session_state must be passed back unchanged, and the return shape is described. It implies mutation via add/remove/edit but does not mention reversibility, permissions, or failure modes. This is solid but not exhaustive.

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?

Two sentences: the first states the tool's purpose and operations, the second describes the initialization pattern and return type. No filler, front-loaded, every sentence adds value.

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?

Given the tool's complexity (conversational, stateful, no output schema), the description covers the essential workflow: how to start, how to continue, and what the response contains. It provides enough guidance for an agent to invoke the tool correctly and handle the session. Minor omissions like error handling are acceptable at this level.

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 schema descriptions cover all three parameters (100% coverage), so baseline is 3. The description adds interaction semantics beyond the schema: that the first message must be empty to load the CAP, and that session_state is opaque and must be passed back unchanged. This clarifies the multi-turn protocol.

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 clearly states the tool edits an existing CAP and lists specific operations: add questions with AI-generated knowledge probes, remove questions, and edit multiple-choice options. The verb 'edit' and resource 'existing CAP' distinguish it from sibling cap_capture_expert (which presumably captures/creates) and generic CRUD tools.

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?

Provides clear usage context: conversational editing of an existing CAP, with explicit instruction to pass an empty message on first call and session_state on subsequent calls. It does not explicitly name alternatives or state exclusion criteria, but the intended scenario is evident from the description.

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