direct.hf.find_keywords

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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered. The description adds only the faint hint that human-readable names/substrings are accepted (vs raw ID-based listing), but doesn't say whether names are resolved server-side, whether matching is case-sensitive, or how results are capped.

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?

A single tight sentence with the filter axes front-loaded. The 'Human-friendly:' tag is slightly wasteful but not enough to hurt materially.

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?

Output schema exists so return values need no explanation, and annotations cover the read-only profile. Still, for an 8-parameter find tool with 25% schema coverage, the description leaves limit/pagination and name-vs-id precedence unaddressed.

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 25% with 8 optional params, so the description has to carry weight. It does gesture at the campaign/adgroup pair and the 'contains' substring, which covers the main filter families, but says nothing about limit, or how id vs name variants interact.

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 concrete verb ('find') and resource ('keywords') plus the filter axes (campaign/adgroup and substring), which distinguishes it from direct.list_keywords and report_keywords. The 'Human-friendly' prefix is soft framing rather than substance, but the core purpose is unambiguous.

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?

No explicit when-to-use or when-not-to-use. The description implies a name/substring lookup, but it never says to prefer this over direct.list_keywords or direct.hf.report_keywords, nor what happens with no filters supplied. The agent must infer the routing decision.

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