code_task

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

With no annotations, the description carries the full burden, and it does disclose the critical trait: this tool does not mutate or verify anything. It also names the three payload kinds (candidates, structure, impact). It says nothing about cost, whether prior indexing/workspace state is required, or determinism of the returned candidates, which matters for a planning call intended as the first step.

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 short sentences, front-loaded with the call-to-action and closed with the follow-on chain; nothing is padded. The arrow-chain notation is dense to the point of being telegraphic, which costs a little readability against the otherwise tight structure.

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 6-parameter, nested-object, no-output-schema tool, the description covers the two things an agent most needs: when to call it and what happens next. Parameter-level detail is delegated entirely to a fully-covered schema, and return shape is only named, not characterized — acceptable given no output schema exists but not exhaustive.

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 goal, route, target, request_id, search_terms, and workspace_dir are already documented in the schema, making 3 the baseline. The description mentions only 'describe the goal' and adds no guidance beyond the schema — notably it never explains when to override route or how target anchors steering, even though route inference ('Inferred when omitted') is a meaningful behavioral lever.

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 states a concrete purpose: a planning call that takes a goal and returns candidates, structure, and impact in one shot. It differentiates from siblings by naming the read/patch/check sequence that follows. What it lacks is a crisp verb+resource label (e.g. 'plan a code change'), leaving 'start here for any change' slightly open-ended about the artifact produced.

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 an explicit trigger ('Start here for any change'), an explicit exclusion ('Planning only — does not itself edit or check'), and names the alternatives plus their order (code_read → code_patch / code_batch → code_check). An agent can route correctly without inspecting any other tool.

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