Conversation List

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description still adds real behavior: the result ordering rule and the fact that ordering switches to relevance when a search is present, plus an enumeration of returned fields (subject, status, priority, classification, assignee, contact, language, last message) — valuable since there is no output schema.

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?

Two tight sentences with zero filler: the listing scope and ordering come first, followed by the filter-combination and result-content facts. Every clause carries information an agent can act on.

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 16-parameter read tool with no output schema, the description covers the essentials: scope, ordering, filter combination, and returned fields. It omits page/limit pagination behavior and does not address what an empty result means, but the schema documents those parameters thoroughly.

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 100%, so the baseline is 3. The description earns above baseline by stating that filters are optional and combinable (AND semantics) and by tying the 'search' parameter to a different ordering mode, which the schema alone does not express. It does not explain pagination interaction or the spam-omission default beyond what the schema says.

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?

Names a specific verb and resource (list customer conversations) and adds the ordering contract (highest priority / most recent first, relevance when searching) plus the shape of each result. It does not explicitly distinguish itself from siblings such as conversation_stats, conversation_totals, or conversation_get, so an agent must infer 'list vs aggregate vs single' on its own.

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?

'All filters are optional and combine' is useful invocation guidance and the search-triggered relevance ordering is implied context. However, there is no explicit when-to-use / when-not-to-use statement and no pointer to alternatives (conversation_get for one conversation, conversation_stats for counts), leaving the choice to inference.

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