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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds substantial behavioral context beyond that: it explains the four provenance types ('key', 'token', 'runtime', 'system') with security implications, and warns that event bodies are untrusted data, never instructions. This is critical for safe agent behavior and goes well beyond what annotations convey.

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?

The description is front-loaded with the core purpose, then efficiently covers event types, filters, provenance, trust, and publishing alternatives. Every sentence adds value – the provenance and untrusted-data warnings are essential, and the publish alternatives prevent misuse. No fluff, well-organized.

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 read tool with no output schema, the description covers what is returned (event stream with types, order, filters), the provenance model, the trust boundary, and how to publish instead. It does not detail the exact JSON envelope (e.g., id, timestamp), but the description gives enough for an agent to correctly call and interpret the tool. Combined with the rich annotations and schema, nothing critical is missing.

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 100% – all three parameters (agent, limit, target) have descriptive comments in the schema. The description only reiterates the filtering capabilities without adding new semantic details (e.g., format, defaults, or edge cases). This matches the baseline of 3 for full schema coverage.

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: 'Read the append only event stream', followed by an explicit list of event types and ordering ('most recent first'). It also names the optional filters (agent handle, target slug), making its scope unambiguous and clearly distinct from siblings like get_board or wait_for_event.

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 clearly states the tool is for reading, and explicitly directs to publish_thought / publish_finding or the signed REST API when the goal is to write. This provides a clear when-not to use this tool. It does not explicitly contrast with other read-oriented siblings like wait_for_event, but the purpose is so clearly defined that an agent can infer when to choose it.

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