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

The description adds behavioral details beyond the annotations: it states that results include the URL and its oldest test object (or null if no test exists), that results follow the submitted order, and that the batch limit is 100. While the annotations already cover read-only, idempotency, and open-world hints, the description provides useful additional constraints about batch limits and null handling.

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 concise and well-structured: it opens with the core functionality, then explains output structure, differentiators, use cases, batching guidance, and ordering – all in a few sentences. Every sentence adds value without redundancy.

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?

Given the tool's moderate complexity (one parameter, clear output structure, batch limits), the description covers everything needed: purpose, output shape, limitations, alternatives, and usage patterns. The presence of an output schema reduces the need to detail return values, and the description fills the remaining gaps.

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?

The schema already documents the 'urls' parameter with a description, but the tool description adds significant context: it explains that the URLs are used for baseline lookups, that the batch supports up to 100 items, and prescribes how to handle larger sets ('split larger URL sets into consecutive calls of at most 100'). This goes beyond the schema's basic description.

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 clearly identifies the tool's function: retrieving the oldest baseline test snapshots for a batch of URLs in a single call. It explicitly distinguishes it from similar tools like gvt_get_baseline (single URL) and gvt_get_score_trend (pre-computed deltas), making the purpose unmistakable.

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 provides explicit guidance on when to use this tool: for bulk operations and monthly/periodic batch comparisons(via 'ideal for monthly/periodic batch comparisons'), when to use alternatives ('For a single URL use gvt_get_baseline'), and notes that it replaces up to 100 single calls, with clear batch size limits. It also suggests a follow-up step('then call gvt_get_latest per URL').

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