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

Annotations already flag destructiveHint=true and non-idempotent, but the description goes well beyond them: it says a running visual index stops at the next sample and keeps its checkpoint, that the asset then shows an incomplete-analysis badge, and that retry_analysis restores it. That is exactly the kind of blast-radius and recoverability context an agent needs before destroying 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?

The action semantics are front-loaded and every later sentence adds operational detail (checkpoint preservation, badge, retry path) rather than restating the schema. Only the opening 'Full control of the background work queue' is filler that duplicates the title.

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 return-value burden and largely discharges it by describing what 'list' returns (queued/running items across projects plus visible task rows with a cancellable flag). It does not say what a 'cancel' call returns, so an agent cannot predict the confirmation payload.

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 genuine meaning: 'ONE kind of work for ONE asset' constrains cardinality so an agent knows multiple cancels require multiple calls, and the kind enumeration is repeated inline with cancel-only scoping. It omits any explanation of projectId's role, which is why it is not a 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?

Names the resource (background work queue) and both actions precisely: 'list' enumerates queued/running work items plus visible task rows, 'cancel' stops one kind of work for one asset. The verb-and-resource pairing is specific enough to act on. It falls short of a 5 because it never distinguishes itself from plausible siblings like get_job_status, get_analysis_status, or get_problems, which an agent could easily confuse with queue listing.

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 context is clear: use 'list' to inspect queue state, use 'cancel' to stop work, and use retry_analysis or a tile retry button to re-run something afterwards — an explicit alternative for the follow-up case. It lacks explicit exclusions, i.e. no statement of when to prefer get_job_status or get_problems over list.

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