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

Discloses cost ('spends the workspace's Replo credits... or one credit when a grade already exists'), the asynchronous nature ('returns a request; poll... every few seconds'), and the side-effect boundary ('returns data only: nothing is shown to the user yet'). These are behaviors the annotations (readOnly=false, idempotent=false) do not convey, and nothing contradicts them.

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?

Front-loaded with the purpose ('Start an X-ray...') before the input rule, cost warning, and workflow. Sentences are dense and each carries operational weight, though the piece is long enough that a reader must hold several instructions at once; minor trimming is possible but nothing is 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?

With no output schema, the description still supplies everything needed to complete the task: the return is a request, the polling loop via sightglass_get_xray, and the final sightglass_show call using the resultId. The credit-cost and workspace-plan dependencies are also covered, so the agent can run the whole flow without inference.

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 already 100%, so the baseline is 3, but the description adds a genuine constraint the schema omits: 'Pass exactly one of adId or sitePageId.' That mutual-exclusivity rule is not expressed by the schema (both are optional) and meaningfully affects correct invocation. It does not add format details beyond the schema, so 4 rather than 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?

States a specific verb+resource ('start an X-ray: a graded teardown of one ad... or one landing page'), the scope (funnel vs. standalone page), and what it produces ('scored against what works in its category'). Distinguishes itself from the get/find siblings by describing the graded teardown action, not a lookup.

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?

Explicit when-to-use ('only call it when the user asked for a grade'), the mutually-exclusive input rule ('Pass exactly one of adId or sitePageId'), and the full follow-up workflow (poll sightglass_get_xray until it finishes, then call sightglass_show once with the resultId). Alternatives like sightglass_get_xray and sightglass_show are named and sequenced.

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