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

Annotations already include readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the description need not repeat safety. It adds useful context: 'Sources are omitted unless explicitly requested by version id or latest version.' This indicates that the tool may not include all sources by default兒, which is a behavioral nuance not in the annotations. However, it does not describe return format or pagination, but given the annotations, a 3 is appropriate.

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 one sentence, concise, and front-loads the core purpose. It does not waste words. The sentence is clear and readable. It could arguably be more structured (e.g., bullet points) but is appropriately sized.

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 has 6 parameters, no output schema, and moderate complexity, the description provides enough to understand the primary function but lacks specifics on return values. For a read-only, idempotent tool, the missing details (like what the exact return structure is) are somewhat less critical, but an agent might be uncertain about what data will be included and how to handle the options. With annotations covering safety, a 3 is appropriate but there is room to clarify the effect of parameters like maxTrialsPerExperiment and versionSourceIds.

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 only 33%, so the description must compensate. The description does not provide detailed explanations for most parameters (caseStudyId, versionSourceIds, maxTrialsPerExperiment, etc.). It mentions that sources are omitted unless requested, which relates to versionSourceIds and includeLatestVersionSource, but does not clarify their meaning beyond the schema. The baseline 3 is appropriate because the description adds minimal value; the schema has some descriptions for researchRunId and mcpIdempotencyKey, but the other parameters are undocumented in both.

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 states it loads a case study summary and related data (versions, experiments, trials, evidence). The verb 'load' and resource 'Case Study' are specific. It distinguishes from siblings like ata_load_case_study and ata_list_case_studies by mentioning the active case study and version handling, though it doesn't name a sibling explicitly.

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 implies it is for retrieving case study related information, but does not explicitly state when to use it versus alternatives (e.g., when to use ata_load_case_study instead). It mentions optional parameters like versionSourceIds and includeLatestVersionSource, but does not give clear guidance on when to use them or when not to use this tool. It covers some usage context (e.g., 'Sources are omitted unless explicitly requested') but lacks explicit alternatives.

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