ask_agent

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

With no annotations, the description carries the behavioral burden and does disclose two non-obvious traits: helpers cannot see the repo (context isolation) and the caller remains responsible for verifying output (quality caveat). It does not cover failure modes, latency, or the parallel-call implications of model='all', which the schema only partly addresses.

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 short sentences, front-loaded with purpose and cost rationale, then the context requirement and the verification caveat. Every sentence carries actionable information; the example list is compact and aids routing rather than padding.

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?

For a 4-parameter tool with a fully documented schema and no output schema, the description covers purpose, context requirements, and the verification obligation well. It is slightly thin on what the caller receives back (a text answer) and on behavior when model='all' fans out to multiple helpers.

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 description coverage is 100%, so the baseline is 3. The description reinforces that `prompt` must be complete and self-contained and that `system` carries optional extra instructions, but it adds no syntax or format detail beyond the schema.

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?

States a specific verb (delegate) and resource (a self-contained chore to a cheaper helper model), plus the concrete payoff (save Claude tokens). The examples of delegated work and the contrast with sibling tools like web_search/web_fetch/generate_images make the boundary unambiguous.

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?

Gives clear when-to-use context through enumerated task types (summarising docs/logs, drafting boilerplate, translating, brainstorming, explaining an API) and warns to supply full context. It stops short of naming an explicit alternative or a when-not-to-use condition, so it is clear context rather than full routing guidance.

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