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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description only needs to add real behavior — and it does: short exports return inline while long ones return a download link valid for 10 minutes. That response-shape variability and TTL is exactly the kind of detail an agent needs when presenting output to a user.

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?

Two tight sentences, front-loaded with the primary action and followed by the conditional return behavior. No filler or repetition of structured 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?

With no output schema, the description correctly compensates by explaining the two possible return forms and link expiry. It remains silent on edge cases (no ready clips, link auth) and on how this differs from export_episode_markdown, which is the last meaningful gap for a single-parameter read 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?

Only one parameter (episodeSeq) and the schema documents it fully with a format example, so the schema carries the semantics. The description adds nothing about the parameter, which is acceptable at 100% coverage but merits only the baseline.

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 (export) and resource (all ready clips of an episode) with the output format (one Markdown document). The 'ready clips' scoping is informative, but it never distinguishes itself from the sibling export_episode_markdown, leaving the agent to guess which export covers clips vs. the whole episode.

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?

Usage is only implied: it's evidently for producing a shareable Markdown copy of an episode's clips. No explicit when-to-use, prerequisites, or comparison against export_episode_markdown / export_episode_srt, so the agent has no routing guidance among the three export siblings.

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