search_messages

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that results come from a local decoded-body index kept up to date automatically, that the first search on a large history is slow while later ones are fast, and that results render as an inline card that shouldn't be repeated. It does not state the ordering of global (non-chat-scoped) results or any permission/auth constraints.

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-loads the purpose, then index/latency behavior, then rendering guidance, then the arg list — a sensible order with no filler. The rendering note is arguably tangential to tool selection but is genuinely useful invocation context, so the extra length is defensible.

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 six-parameter search tool with no annotations and 0% schema coverage, the description covers purpose, latency behavior, output rendering, and every parameter. The output schema handles return values, so the only mild gap is the unspecified ordering of results when no chat_id is given.

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 0%, so the description must supply all parameter meaning, and it documents every one of the six: query as case-insensitive substring, limit as max results with default 30, chat_id scoped to list_chats, from_me sent/received polarity, and after/before as inclusive 'at or after'/'at or before' bounds. The inclusive boundary semantics are extra information the schema's date-time types do not convey.

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 with explicit scope: 'Search message bodies across every conversation, over all history.' It distinguishes itself from the narrower retrieval siblings by emphasizing 'every conversation' and full history, though it never names an alternative like get_chat_messages. Adding the case-insensitive substring detail further pins down what 'search' means here.

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 conditions: leave query out to search filters alone, and 'chat_id plus a date range with no search term reads one conversation newest-first.' It also points to list_chats as the source of chat_id. It stops short of explicitly saying when to prefer this over get_chat_messages or refresh_search_index.

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