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

Annotations already declare readOnly, idempotent and non-destructive, so the safety bar is low; the description still adds two non-obvious semantics: 'Listing claims no work' (browsing does not claim or reserve runs) and 'Queued does not mean completed' (a status caveat that prevents misreading results). It does not discuss pagination or default ordering, though the schema covers those.

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 clauses with no filler: purpose first, sibling routing second, caveats last. Every sentence carries distinct information and nothing repeats the schema or annotations.

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 and the schema documents pagination and filters, so the description does not need to explain return values. What it provides — purpose, alternative, and the 'Queued does not mean completed' caveat — is enough to call the tool correctly, though a note on default page size or the fact that all filters are optional would round it out.

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 100%, so the schema already documents all eight parameters including cursor/limit/order pagination mechanics. The description only gestures at the filter categories ('Task, group or status') without adding format or interaction rules beyond what the schema states, which is the expected baseline-3 case.

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 ('Browse') plus the resource ('Runs') and the three filter dimensions (Task, group, status), which map directly onto the schema's task_id, run_group_id and status parameters. It also explicitly routes detail lookups to swarm_get_run, so the agent can separate this list tool from the get sibling 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?

'inspect details with swarm_get_run' names the alternative and the condition that selects it, which is the main routing decision for a list/get pair. It stops short of stating when *not* to use listing (e.g. when you already have a run ID) or what the filters are mutually exclusive with, so it is clear but not exhaustive.

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