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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior. The description adds substantial operational context: exact snapshot_id and catalogue group IDs required, benchmark/overlap/filters must be preserved, correlation requires an explicit asset pair and supported window, facts.summary carries line points and membership counts, and API analytics are authoritative while endpoint differences are not correlations.

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?

Organized into clear sections (Use/Do not use, Selection, Presentation, Evidence) with the primary use case front-loaded. The presentation guidance is dense and slightly verbose, but it earns its place for a complex analytical tool. Minor trimming of presentation details would improve conciseness without losing critical information.

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 output schema exists, the description needn't explain return values, yet it usefully mentions facts.summary contents and evidence sections. It covers selection constraints, correlation requirements, shared-membership treatment, and interpretation guardrails sufficiently for a tool with complex nested parameters.

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%, so the baseline is 3. The description adds procedural meaning beyond the schema: use the returned snapshot_id, exact catalogue group IDs, second-based bounds inside the prepared history, preserve unchanged selection fields, and request correlation with an explicit asset pair. It does not detail every nested field, but the added selection guidance is actionable.

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 specific analytical tasks (group performance, relative returns, contributions, metric relationships, qualified pair correlation) and explicitly scopes the tool to a pinned history. The do-not-use list (inventing sector membership, re-preparing history, causal claims, portfolio advice) further distinguishes it from research_prepare_cohorts and other siblings.

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?

Provides explicit when-to-use and when-not-to-use guidance, names research_prepare_cohorts/status as the source for snapshot_id, instructs to refine existing comparisons while preserving unchanged fields, and gives selection rules for time bounds and correlation pairs. Nothing critical is left to inference.

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