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

Annotations already declare readOnlyHint/openWorldHint=false/destructiveHint=false, so the safety profile is covered; the description adds non-obvious behavior such as low-quality responses being archived and excluded from all other filter combinations unless requested, and the cost/implication of includeConversation (bulk-fetched transcripts). It stops short of stating rate limits or truncation behavior when limit caps at 50.

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-loaded with purpose, then filters, then return shape, then the includeConversation caveat, then examples — a sensible ordering. It is dense and long-ish for one paragraph, but every clause carries information; no filler sentences.

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?

An output schema exists so return values are supplementary, yet the description still summarizes them usefully; annotations cover safety, and the description covers the tricky parts an agent could get wrong (archived low-quality exclusion, when to request conversations). Nothing material is missing for a 10-param optional-filter read tool.

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?

With 100% schema coverage the baseline is 3; the description goes further by explaining cross-field semantics the schema states only per-parameter: keyword matches summary + respondent name/email, contactId comes from contact_list, projectId null means whole org. It aggregates the filter model rather than repeating individual descriptions.

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+resource with scope ('Search/filter individual responses across the whole org or one project') and enumerates the filter dimensions and return fields. It implicitly separates itself from recent_responses (unfiltered recency list) and response_detail (single transcript) by describing bulk filtered search, so an agent can route correctly.

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 concrete trigger phrasings ('negative responses about X', 'responses from <contact>', 'low-quality responses since <date>') and a clear conditional for includeConversation ('use this when EXPORTING'). It does not explicitly name when NOT to use it or point to recent_responses as the unfiltered alternative for the same task.

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