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

Annotations already declare this is non-read-only, destructive, non-idempotent, and closed-world. The description adds useful behavioral context: Agentery re-runs the search while keeping other constraints, returns the new answer plus what changed, only sees the request/correction rather than the wider conversation, and references expire after 24 hours. It does not fully detail what is destroyed or invalidated by the re-run, so it falls short of a 5.

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?

The description is front-loaded with the core usage condition and correction examples, then moves into mechanics, privacy scope, task-answer protocol, and expiry. It is dense but appropriate for a multi-step continuation tool. There is some repetition, notably restating the source enum and 'plain words' guidance, which keeps it from being maximally concise.

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?

The description is complete for an agent to call the tool correctly: it covers prerequisites (request_ref), correction format, source semantics, continuation behavior, privacy scope, and expiry. An output schema exists and annotations exist, so return-value details and safety traits are already covered by structured fields.

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 adds meaning beyond the schema by explaining the source values ('human' = user's words, 'agent' = your assessment/default, 'follow_up'), giving correction examples such as 'must integrate with Slack' and 'budget is $20/month', and clarifying that request_ref comes from the earlier answer.

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 specific action and resource: refine results by passing a request_ref and correction so Agentery re-runs the search with changed constraints. It explicitly names sibling tools (search_providers, research_capability) and distinguishes this tool as the correction/refinement path rather than a fresh search.

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 explicit when-to-use guidance: 'Use when an earlier search_providers or research_capability answer missed what was meant.' It explains exactly what to pass (request_ref plus correction in plain words), provides examples, and names the alternative continuation path: pass the same request_ref to another task tool.

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