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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds real value beyond them by disclosing the searchable corpus (datasets, fields, categories, plans guide) and the return shape (ids, titles, URLs), which matters since no output schema exists.

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, zero waste. The corpus scope leads and the follow-up action is front-loaded at the end.

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 one-parameter search tool with no output schema, the description covers what is searched, what comes back, and what to do next. Missing are result caps/pagination and matching semantics, which an agent would need for large or ambiguous queries.

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 0% and the single parameter is undocumented, but the description's word 'Keyword' signals free-text matching rather than exact id lookup. That is useful but thin; nothing is said about multi-word behavior, matching rules, or result limits.

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 ('Keyword search over every dataset, its fields, the categories and the plans guide'), and scopes the corpus precisely. It routes the agent onward to 'fetch', though it does not distinguish itself from siblings like list_datasets or find_symbols.

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 follow-up path is explicit: results give ids and 'read one with fetch.' That tells an agent when this tool is the entry point versus fetch. It stops short of naming when-not conditions or contrasting with find_symbols/list_datasets.

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