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

Beyond the readOnly/idempotent annotations, it discloses two genuinely useful behaviors: a succeeded job issues a fresh private download URL valid 15 minutes, and the export itself expires after seven days. It omits the status set (pending/running/failed) and what a non-succeeded job returns, which is the main remaining behavioral 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?

Three short sentences, front-loaded with the action, then the two expiry facts. No filler and nothing redundant.

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?

An output schema and read-only annotations already cover return shape and safety, so the description only needed to add lifecycle context — which it does via the 15-minute URL and 7-day expiry. It falls short only on polling guidance and on documenting the two required UUID parameters.

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 only 33% — job_id and study_id carry no descriptions, only UUID patterns — and the description adds nothing about them. "Poll an ... export" weakly implies job_id identifies the export job, but there is no guidance on study_id scoping or when organization_id is required.

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?

"Poll an editable PowerPoint export" gives a specific verb (poll) and resource (PowerPoint slide export job), which separates it from the broader get_report_job and from queue_report_slides. It doesn't name those siblings explicitly, so an agent must infer the boundary rather than read it.

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?

"Poll" implies this is called repeatedly after an asynchronous queue operation, and the sibling queue_report_slides is the plausible trigger. However, the description never states when to call it, how often, or why one would pick it over get_report_job or get_study_report — usage is only implied.

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