search_conversations

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 that hits are raw text 'as said, not extracted, checked or versioned', that they are dated records rather than current state ('check that live'), and that chunks resolve to message spans. These are non-obvious semantic traits an agent could not infer from the schema alone.

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: purpose first, then time-filter usage, then the sibling routing, then the truth-vs-record caveats. Each sentence addresses a distinct concern, though the closing three caveat clauses stack up and could be tightened.

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 5-parameter search tool with no annotations and no output schema, the description covers invocation, alternatives, time filtering, and return-value semantics. An agent has everything needed to call it correctly and interpret hits.

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 a baseline of 3 applies, but the description adds real value by explaining when to prefer since over days and giving a natural-language example of mapping a relative date to since. The scope parameter is not addressed in the description, keeping it below a 5.

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 dual resource ('Search the user's synced conversations AND coding-agent sessions') plus the retrieval modes (keyword and semantic similarity). It also pins down result shape (source_type tagging, resolution to message span rather than title), which lets an agent distinguish it from get_conversation and list_recent_conversations without opening a 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?

Explicit routing to alternatives: browsing with no query goes to list_recent_conversations, and decisions/learnings/outcomes go to memory_search. It also gives a concrete time-filter recipe ('yesterday's chat about X → query = X, since = yesterday's date'), leaving little to inference.

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