recall_candidates

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

Annotations declare readOnlyHint=false but destructiveHint=false, and the description is consistent with that by disclosing a "log metadata" side effect, which is real value beyond the annotations. It still omits what metadata is recorded, where it persists, and what happens to the capped-out results beyond the first five.

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 with no filler, and the core capability is front-loaded before the parameter caveat. The terseness borders on under-specification rather than verbosity, which is the right failure mode.

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?

An output schema exists, so return-shape details are rightly omitted, but this tool has a write side effect and three parameters at 0% schema coverage. The description lacks prerequisites, task_id semantics, and any placement of the tool in the broader prepare/confirm/expand flow, which its siblings imply exists.

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 0%, so the description carries the burden; it does explain the least obvious parameter (manual=True only for explicit user searches). However, query and task_id receive no explanation, and the five-item cap is stated as a fixed behavior rather than a controllable parameter, leaving two of three parameters undocumented.

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 retrieval verb and a concrete result bound ("up to five cards"), but never defines what a "candidate" is in this domain and gives no signal distinguishing it from siblings such as get_card, list_cards, or prepare_card. The added "log metadata" clause muddies whether this is a pure read or a read-with-side-effect.

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?

The only guidance is a parameter-level rule: manual=True is reserved for explicit user searches. There is no statement of when to call recall_candidates at all, what it queues up for (e.g. confirm_card or expand_recommendation), or when another tool is the better choice.

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