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

Beyond the annotations (destructiveHint, idempotentHint) the description discloses that skipped checks are never made up, that an in-progress check is cancelled, that failures are reported in 'failed', and that retrying is safe. This is rich behavioral context that goes well past the structured hints.

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 dense paragraph that front-loads the core action before the caveats. Every clause carries information; no filler.

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 annotations cover safety hints, so the description only needs to supply operational behavior, which it does thoroughly (budget impact, cancellation, no makeup, failure reporting, retry safety).

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 0% and organizationId/projectId are not explained at all. The description does compensate partially by clarifying the collection semantics (up to 100, per-id failure reporting), but leaves scope and identity parameters unaddressed.

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 ('Pause ... tracked queries') with an explicit scope ('up to 100'). It names the counterpart sibling resume_tracked_queries, so an agent can distinguish pausing from resuming without opening either 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?

It gives a clear operational context (checks stop and spend no budget) and points to a follow-up tool (get_usage) and the restart path (resume_tracked_queries). It does not state a when-not condition or prerequisites, so it falls short of the full when/alternatives bar.

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