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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds substantial behavioral context beyond that: results are raw events ordered newest-first, each includes latest deliveries, results are bounded by plan retention, and pagination has a non-obvious signal where a short page with a cursor means the search window ended. This is exactly the kind of nuance an agent needs to interpret results correctly.

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 dense sentences carry all the information with no filler. The core purpose and ordering are front-loaded, and the non-obvious pagination caveat is placed second where it can be noticed before use. Every clause earns its place without repeating schema content.

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 13-parameter search tool with no output schema, the description covers ordering, retention bounds, pagination behavior, and result shape, which is unusually complete. It leaves minor gaps such as the exact meaning of include_payload and how filters combine, but these are small relative to the operational detail already provided.

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 77%, so the schema already documents most parameters. The description adds value by grouping the filter dimensions, clarifying that user_id is the sender's customer identifier, and explaining that results include each event's latest deliveries, which informs interpretation beyond individual parameter descriptions. It doesn't detail include_payload's effect, but the schema covers most of the parameter semantics.

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 states a specific verb ('Searches'), a precise resource ('organization's recent raw events'), and enumerates the filter dimensions: text, event name, level, delivery status, user_id, route, source, and time. It also specifies the ordering (newest first) and that each event includes its latest deliveries, which clearly differentiates it from siblings like event_stats or get_event even without naming them.

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?

The description gives strong operational context, such as retention bounds and pagination semantics, but it never explicitly says when to prefer search_events over get_event, event_stats, or get_user_timeline, nor when not to use it. Usage context is implied rather than stated with alternatives or exclusions.

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