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

Annotations declare non-read-only, non-destructive, non-idempotent, closed-world; the description meaningfully adds that the operation is asynchronous, spawns a background job, and sends an email to the current author — a side effect worth knowing. It stops short of saying whether repeated calls queue duplicate jobs (relevant given idempotentHint=false) or who 'the current author' resolves to.

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?

A single well-formed sentence with the actor, action, output artifact, and delivery mechanism front-loaded; there is no filler and nothing to trim.

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?

With an output schema present and full parameter documentation, the description covers the essentials an agent needs: cost model (async job), where results go (email link), and format (XLSX). Minor gaps remain around scope of 'all responses' (complete vs. partial) and authorization requirements for emailing the author.

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% and both parameters are documented there, including the useful pointer that event_id comes from search_events. The description adds no parameter-level detail, so the baseline 3 applies.

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 pipeline (queue a background job that exports), the resource (all survey responses), the output format (XLSX), and the delivery channel (emailed link to the current author). This clearly separates it from read-only siblings such as read_surveys or read_analytics, which return data inline rather than producing a file.

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 makes the usage model clear: the call queues work asynchronously and delivery happens by email, so an agent knows not to expect response data back. It offers no explicit exclusions or alternative tools (e.g., when to use read_analytics instead), which keeps it below a 5.

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