query_conversations

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

Discloses behavior the annotations cannot: this is a client-side scan that fans out into list + bulk-get calls, and it is cost-bounded by maxScan (default 200). That explains latency and truncation risk, which is exactly the kind of non-obvious trait an agent needs before calling a 12-parameter filter tool.

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?

Four short sentences, each carrying distinct information: what it is, how it works, how it's bounded, and when to use it versus what isn't supported. The most important disambiguation ('NOT a SQL analytics API') is front-loaded.

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?

Good coverage for a 12-parameter filtering tool with a nested object and no output schema: mechanism, cost bound, and unsupported filters are all stated. It doesn't say what a match actually returns (full conversation objects vs. summaries) or that results may be silently truncated when maxScan is exhausted before limit is reached, but nothing essential to correct invocation 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?

With 100% schema description coverage the baseline is 3, but the description adds real meaning by identifying which filters (summaryContains, capturedVariableExists, userName) trigger the expensive detail fetch versus which are cheap, and by restating the maxScan bound as a scan limit rather than just a number.

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 what the tool does concretely: an MCP-side filter over conversations, and explicitly negates the wrong mental model ('NOT a SQL analytics API'). It also names the mechanism (cursor-pages list_conversations, then bulk-gets details) which distinguishes it from the plain list_conversations sibling, though it does not name the nearest alternative (get_conversations_bulk) directly.

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 a positive use case ('Use for audits like summaryContains or capturedVariableExists') and a clear negative boundary: filters like hasQuote and eventDateWithin are not supported and need a future backend endpoint. It stops short of explicitly telling the agent to use list_conversations for unfiltered listing, leaving that inference to the reader.

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