events

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

With no annotations provided, the description carries the transparency burden. It usefully discloses that events more than 24h past are filtered, every record has source and confidence fields, and passing id bypasses date_range and other filters. This goes beyond the basic schema and helps the agent understand edge cases.

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 compact and front-loaded, using three sentences to convey purpose, data transparency, and the critical id exception. Every sentence adds value, with no redundant filler or repetition of schema fields.

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?

Given seven parameters, no annotations, and no output schema, the description does a good job covering purpose, filtering behavior, record attributes, and the id override. It could be slightly more complete by explicitly stating the return shape (e.g., a list of events), but the mention of 'every record' and the response-count note in the schema compensate. Overall it is sufficiently complete for a read-oriented filter tool.

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?

The input schema already documents all seven parameters with 100% coverage, so the baseline is 3. The description adds minimal parameter-level meaning beyond what the schema provides; it repeats the id override behavior already in the schema and does not offer new syntax or formatting details for other parameters.

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 clearly states the tool finds upcoming Austin events from Yeehaw's sourced, deduplicated store, using a structured filter over the events table. It is specific about the resource and scope, distinguishing it from the only sibling 'overview' by positioning it as the queryable event store.

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 provides clear context for when to use the tool and explains the special 'id' mode that ignores other filters. It does not explicitly mention when not to use it relative to the sibling 'overview' tool, but the filtering semantics and id behavior give sufficient practical guidance.

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

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

With no annotations, the description carries the transparency burden. It clearly frames the operation as a read-only report of state, which implies no mutation, but it does not disclose potential side effects, access requirements, latency, or whether the returned data is sampled or comprehensive. The listed contents help but leave open questions about behavior.

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 a single, dense sentence that wastes no words. It front-loads the core purpose ('Inspectable State') and then packs a comprehensive list of report contents into an em-dash-separated tail, making it both efficient and scannable.

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 complex operational state report with no output schema and no annotations, the description lists categories but does not specify return format, field names, pagination, or error behavior. It is sufficiently complete for basic selection but leaves gaps for an agent that needs to parse or rely on the response.

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?

There are zero parameters, so the baseline is 4. The description reinforces the no-input expectation and implicitly explains that the tool returns a broad snapshot rather than requiring filters. Since the schema is just an empty object, the description adds meaningful context about what the tool covers.

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 uses a specific verb ('report') and identifies the resource ('Yeehaw's operational state') with a clear scope ('in one call (no input)'). It enumerates the contents (event counts, ingest status, cron health, circuit breakers, error tail, coverage gaps), which fully differentiates it from the sibling tool find_events.

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 implies usage as a quick no-input state check but provides no explicit guidance on when to use this tool versus find_events or other alternatives. The sibling tool is not mentioned, and there are no exclusions or alternative suggestions.

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