events_recent

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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered; the description adds genuinely new behavioral facts — events are buffered, ordering is oldest-first/newest-last, and the response carries a latest_seq cursor for continuation. It does not mention buffer bounds or what happens if since_seq has fallen out of the buffer, which would be the remaining gap.

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?

Front-loaded with the core action and ordering, then the kind vocabulary, then the return contract — a logical order with no filler. The kind enumeration is long but is the only documentation of valid filter values, so it earns its space.

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?

Output schema exists, so return shape needn't be explained, and the description correctly covers ordering and the cursor. But for a 6-parameter filterable list tool with zero schema coverage, the absence of any explanation of the filter parameters leaves an agent unable to use half the surface confidently.

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 0% across 6 parameters, so the description must carry the burden. It explains since_seq and effectively enumerates the legal values for the kinds filter, but limit, pane_id, workspace_id, and agent_status filters are documented nowhere, and the combination/AND semantics of the filters are unstated.

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 resource: buffered Herdr events after a sequence cursor, returned newest-last. It implicitly separates polling-style retrieval from the blocking siblings events_wait and events_status, but never names them, so sibling differentiation is left to inference.

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 cursor-driven phrasing ("after since_seq", "latest_seq to use as the next cursor") implies the incremental-polling use case, which is the main thing an agent needs to know versus events_wait. However, there is no explicit when-to-use or when-not-to-use guidance and no mention of the sibling tools.

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