Retry ai tracking run

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

Annotations already declare write (readOnlyHint=false), openWorld, and non-destructive behavior. The description usefully adds that immutable revisions are preserved, explicit budget consent is required, and no automatic paid baseline is started, which is real context beyond the annotations. It stops short of describing failure modes, idempotency behavior, or what the retry actually re-executes.

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 sentences with no filler and the constraint ('does not start an automatic paid baseline') placed up front. It is efficiently sized, though the first sentence spends its words on a generic category rather than the operation.

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?

A 13-parameter, 11-required write tool with no output schema needs the description to explain workflow: that this follows preview_ai_tracking_run, that revision/consent/credential fields must match the reviewed preview, and what a retry re-executes. The description supplies none of that, leaving the agent to reverse-engineer the flow from parameter descriptions.

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% and every parameter is well documented inline (idempotency_key, consent, budget_revision, credential_version, etc.). The description's phrases 'stable retry keys' and 'explicit budget consent' gesture at parameters but add no meaning the schema does not already provide, so baseline 3 applies.

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?

The description opens with the generic 'Manage project-scoped AI tracking,' which never states the actual operation (retrying a tracking run) and would apply equally to a dozen sibling ai_tracking tools. Only the tool name carries the verb; the description itself is closer to a tautology than a specific verb+resource statement.

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?

There is no when-to-use guidance and no reference to the obvious siblings (preview_ai_tracking_run, create_ai_tracking_run, cancel_ai_tracking_run). The one negative statement ('does not start an automatic paid baseline') gives a single scoping hint but no condition for choosing this tool versus alternatives.

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