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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorld=false, so the safety profile is covered for free. The description still adds value beyond them: the hard result cap of 30 items, the fact that statuses and credit receipts are included, and 'No new collection' clarifying it will not trigger any research work.

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 front-loaded sentences with zero filler: what it returns, where to go for depth, and what it will not do. Every clause earns its place.

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 exists, so return values need no explanation, and annotations carry the safety profile. The description covers scope, cap, and the no-side-effect guarantee, leaving only minor unstated details such as what happens if fewer than 30 runs exist or whether the list is ordered chronologically beyond 'latest'.

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 is exactly one parameter (brandId) at 0% schema description coverage, so the description carries the burden. 'For this brand' does establish that brandId scopes the listing, which is genuine added meaning, but the identifier's format or source is never explained, so the coverage gap is only partly closed.

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 (List) and resource (saved research runs), plus scope details — latest 30, for this brand, including statuses and credit receipts. It also routes the agent to the sibling get_research_run for detail, so it is distinguishable from the many list_* siblings without opening a schema.

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?

Explicitly names the alternative (get_research_run) and its purpose (evidence and the brief), and 'No new collection' implicitly rules out using this when the agent needs to actually start research (start_research). It gives clear context but no explicit statement of when this tool should not be chosen.

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