search_messages

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

With no annotations, the description carries the burden, and it delivers meaningful behavioral detail: matching runs server-side in the Console's sandboxed JavaScript interpreter, only matching messages are transferred, and scanning starts from the oldest message by default. This explains side effects and performance-relevant behavior beyond the 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 tightly packed sentences earn their place: the first states the core function, and the second adds behavioral and performance context. No filler or repetition of schema details.

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 7-parameter search tool with an output schema, the description covers the essential behaviors: server-side matching, transfer of only matching messages, default scan origin, and narrowing. The main gaps are omitted guidance on case_sensitive and max_results behavior, but schema defaults and bounds mitigate this.

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?

At 71% schema coverage, the description compensates partially by clarifying that text matches key or value and that start_offset/start_timestamp_ms narrow scanning. However, it does not add meaning for the two undocumented parameters, max_results and case_sensitive, leaving some semantics to be inferred from schema defaults.

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?

The description opens with a specific verb and resource: 'Find messages whose key or value contains the given text.' It clearly differentiates itself from sibling fetch tools by focusing on text-based search rather than offset/time-based retrieval.

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?

It provides clear context for when to use the tool: searching messages by text content in key or value. It also gives practical guidance to narrow the search with start_offset or start_timestamp_ms on high-volume topics, though it does not explicitly name alternatives or exclusions.

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