Search chats and messages

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

With no annotations, the description carries the full burden and does so: it discloses the searchable corpus (everything in non-ignored chats since linking, the linking history, plus anything load_history fetched), the side-effect profile ('Searching never marks anything read or sends read receipts'), and ordering. It also explains matching semantics beyond syntax, e.g. captions count as text and a document without a caption matches on its file name.

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?

Dense but front-loaded: the core behavior and scope come first, then matching rules, then filters, then corpus limits, then next steps. Nearly every clause earns its place given 11 optional parameters, though the long semicolon-chained paragraph is harder to scan than short separate sentences would be.

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 an 11-parameter tool with no annotations and no output schema, the description covers the important unknowns: what is indexed, result ordering, absence of read side effects, and how to page backward (referencing the 'at' of the oldest match). It does not describe the shape of the response (e.g. the separate chats and messages groups and their identifying fields), which an agent must discover at call time.

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 baseline is 3, and the description earns a bump by explaining matching behavior the schema only gestures at: every word must appear in any order, matching is case-insensitive and mid-word ('inv' finds 'invoice'), and quoted phrases are kept whole. It also clarifies that filters (after/before, from_me, media, links, only_new) work without a query. Some of this repeats the schema's own descriptions, and it never mentions limit, channel, or connection_id by name.

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 concrete verb and resource (search chats whose names match and messages whose text matches) and states the scope variants (all connected accounts, one account, one chat) plus result ordering, newest first. It is clearly distinguishable from siblings like list_chats, read_inbox, and load_history, which are named as different things.

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?

Explicitly says when it will not find things ('Older messages that are only on the phone aren't found') and names the alternative (load_history) for that case, plus how to get conversation context around a match (read_inbox with chat_id and before, or load_history). It also states filters can be used without a query, e.g. every document in a chat last week.

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