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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds non-obvious behavior beyond that: deterministic ordering (newest first) and the direction of paging, which matter for correct iteration. It stops short of disclosing page size or default limits.

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 sentence with the core operation front-loaded, then scope, ordering, and paging guidance in descending priority. No filler or redundancy.

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 carries the burden of describing what a run record contains and what a page returns (size, cursor termination), and it does neither. Ordering and paging direction are covered, so it's adequate but with a clear gap for an agent that must interpret results.

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, but the description adds a genuinely useful recipe not in the schema: `before` should be the smallest id already seen, which pins down the exact paging convention. `projectId` scoping is restated rather than extended, so it's a modest net gain.

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 resource ("List recent agent runs") plus scope (active workspace, newest first, optional project filter). It is clearly distinguishable from get_agent_run by name and behavior, though the description never explicitly contrasts itself with that or other siblings.

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 implied rather than stated: the agent can infer this is the browsing/paging entry point for runs, and the pagination instruction gives a concrete procedure. There is no explicit "use get_agent_run when you have an id" routing or any when-not guidance.

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