Ask how to do a task

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

Goes well past the annotations: explains query widening by key terms, local BM25 re-ranking fused with server ranking and report evidence, weak-match dropping, no key required, and the no_good_match outcome. It also discloses the follow-up contract (get_recipe then quick_report) and notes failures are useful.

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?

Front-loads purpose, then alternatives, then internals, then return/next steps — a sensible order. The middle sentence on ranking mechanics is dense and could be one clause shorter, but every sentence carries actionable content.

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?

With no output schema, the description still enumerates the returned fields (slug, title, summary, url, score, reports, why it matched) and the no_good_match case, plus the follow-up chain. Nothing an agent needs to call and act on the result is missing.

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 coverage is 100%, so the baseline is 3; the description adds framing by specifying that 'task' is plain language and that output count is bounded by max_results. It stops short of extra guidance on ideal task phrasing or when to raise max_results beyond the schema's own note.

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 and resource ('find the best tested recipe / step-by-step playbook') and makes the distinction from search_recipes explicit. The parenthetical examples ('set up daily inbox triage') make the input shape concrete.

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 an explicit trigger ('use it first when your human says use botgathering'), the general condition (need a proven way to do something), and the alternative with its selection criterion ('use search_recipes instead to browse by keyword, category or sort order'). No inference required.

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