List project keywords

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

Annotations declare readOnlyHint=true and destructiveHint=false, so the agent already knows this is a safe read operation. The description adds no behavioral context beyond the annotation coverage—it does not disclose result size limits, pagination behavior (cursor-based), or how filters combine. With read-only annotations carrying the safety profile, the description's marginal added value earns a baseline 3.

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 a single efficient sentence that front-loads the primary action ('List keywords for a project') and summarizes capabilities in a compact list. There is no wasted prose. It could arguably add a bit more value per sentence, but as written it is appropriately lean.

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?

This is a complex tool with 12 parameters, most undocumented in the schema (17% coverage), no output schema, and no explicit pagination or filtering semantics in the description. For a tool of this complexity, the single-sentence description is materially inadequate. It doesn't explain the cursor-based pagination model, how search/filters combine, what ordering defaults apply, or any rate limits.

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 very low at 17%, meaning the description must compensate for poorly documented parameters. However, the description only lists feature categories (pagination, search, filters, sorting) without mapping them to specific parameters like cursor, position_gt/lt, intent, topic, or device. Only project_id has a schema-level description. The description adds some semantic grouping but doesn't bridge the coverage gap meaningfully, warranting a 3.

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 clearly states the verb+resource ('List keywords for a project') and enumerates supporting capabilities (pagination, search, filters, sorting). It distinguishes it from sibling read tools like get_keyword (singular retrieval) and list_ranked_keyword_suggestions. However, it does not explicitly name sibling alternatives for differentiation, so it scores 4 rather than 5.

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 description lists features (pagination, search, filters, sorting) but provides no when-to-use guidance or exclusions. It does not clarify when one would choose this over list_ranked_keyword_suggestions, list_saved_keywords, or search_locations, nor does it mention key requirements like project_id being mandatory. Usage context is only implicit through listing capabilities.

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