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

Annotations already mark this as readOnly, idempotent, and non-destructive. The description adds meaningful behavioral detail beyond that: results are not final while status is pending/running, and callers should wait and retry. It also clarifies the semantics of findingSentence and shareableTid, giving the agent non-obvious knowledge about how to interpret the response. No contradiction with annotations.

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 description is front-loaded with the core action and then efficiently packs high-value details: the exact return fields, retry condition, and usage hints for findingSentence and shareableTid. Every sentence contributes useful information without redundancy or 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 takes on the burden of explaining return values and does so thoroughly: it lists per-category resultData across all 7 analysis types, overall scores, findingSentence, shareableTid, and the pending/running caveat. For a single-parameter read-only tool, this is complete enough for an agent to invoke and interpret the tool correctly.

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 the tid parameter is already well documented as an opaque 8-character hash from gvt_run_visibility_test or gvt_list_tests, not an integer. The description reinforces that results are keyed by tid but does not add substantial new parameter-level meaning beyond what the schema provides, so the baseline of 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 uses a specific verb and resource: 'Get full results for a visibility test by tid.' It goes further by enumerating the exact output categories (7 analysis types, overall scores, findingSentence, shareableTid), making the tool's responsibility unmistakable and clearly distinct from sibling getters like gvt_get_latest or gvt_get_score_trend.

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?

The description clearly establishes when to use the tool: whenever a caller has a tid and wants complete visibility test results. It adds operational guidance about pending/running status implying the caller should wait and retry. It does not explicitly name alternative tools or exclusion conditions, but the context is strong enough without them.

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