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

Beyond the readOnly/idempotent/closed-world annotations, it discloses the costly implementation: a client-side scan that pages list_conversations and then bulk-gets details only for summary/capturedVariables/userName filters, bounded by maxScan. That tells the agent this call is expensive and potentially truncated, which annotations alone would not reveal.

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 tight sentences, front-loaded with the defining distinction before implementation detail, the scan bound, and the use cases/future-endpoint caveat. Dense but no filler; the telegraphic style keeps it short.

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 12-parameter filtered query with no output schema, the description covers cost, scan bounds, filter capability, and unsupported filters. It omits what happens when maxScan is exhausted (partial results or truncation signal) and what shape the returned conversation records take, which matters for an agent deciding whether to widen maxScan.

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 100%, so the per-parameter baseline is 3; the description earns a bump by explaining which filters (summaryContains, capturedVariable*, hasUserName) trigger the expensive bulk-get path, information the schema does not encode. It does not clarify interaction between limit and maxScan when the scan bound is hit.

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 ('MCP-side filter over conversations') and immediately disambiguates the tool class with '(NOT a SQL analytics API)' plus a description of implementation (cursor-pages list_conversations, bulk-gets details). An agent can separate this from list_conversations, get_conversations_bulk, and export_all_conversations without opening the schema.

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 positive use cases ('audits like summaryContains or capturedVariableExists') and an explicit exclusion: filters needing server-side evaluation (hasQuote, eventDateWithin) are unavailable. It stops short of naming the sibling to use for plain unfiltered listing, so routing for the simple case is left implicit.

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