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

Goes well past readOnlyHint=true: it declares the call is free, caps the no-argument listing at 10 recent runs, identifies per-file cost fields and 24-hour download_url expiry when signed links are on, and documents the cross-workspace refusal as NOT_FOUND. Those are exactly the operational traits annotations cannot express.

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 one-word cost signal 'Free.' followed by what is returned, the no-arg behavior, and the refusal case. The parenthetical field lists make it dense but every clause carries information the agent needs; a little more sentence separation would improve scanning.

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 one optional parameter and no output schema, the description carries the return shape itself (status, url, asset_key, charged_micro_usd, expiring download_url) plus scoping and error behavior. Nothing an agent needs to decide to call it or interpret the result is missing.

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 coverage is 100%, so the baseline is 3, and the description adds real semantics on top: absence yields recent runs, and a run_id from another workspace is rejected rather than silently empty. It doesn't add format detail beyond the schema's tpr_ prefix hint, so it stops short of 5.

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 resource and operation: a template run's status (with the enum values needs_label, rendering, done, failed), plus delivered artifacts and charges. It is clearly a read of a run, not a run trigger, but it never names the nearest siblings (template.run, template.list) even though the no-run_id form overlaps with template.list.

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?

Gives explicit conditional usage: with run_id you get that run, without run_id you get this workspace's 10 most recent runs. It also states the failure mode (NOT_FOUND for a foreign run_id), which tells the agent when the call will fail rather than return data. No explicit 'use X instead' routing to siblings.

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