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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds meaningful non-obvious context: the return payload includes concept IDs, titles, summaries, access flags, etc.; the source requires no authentication; and CMR's scale is described. This goes beyond the structured annotations without contradicting 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?

The description is front-loaded with the core action and filters, then return fields, usage routing, and source/authentication context. It is longer than strictly necessary, with the 45,000+ collections and 60+ archives sentence being optional, but it remains dense and scannable without redundant 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?

Given 9 optional parameters, full schema coverage, rich annotations, and an output schema, the description provides all essential contextual information: scope, filters, return values, downstream tools, source, licensing, and authentication. No critical invocation detail is missing.

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 every parameter is documented in the schema. The description merely restates the filter categories (keyword, provider, temporal range, bbox, processing level) and adds some provider examples, but it does not need to compensate for schema gaps. The baseline of 3 is appropriate when the schema carries the parameter-level burden.

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 action ('Search') and a well-defined resource ('NASA Common Metadata Repository for Earth science satellite datasets and collections'). It also names downstream sibling tools, clarifying that this tool is the search entry point and separating it from nasa-cmr.datasets.detail and nasa-cmr.granules.search.

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 clear context on what filters are available and explicitly connects results to nasa-cmr.datasets.detail and nasa-cmr.granules.search. It stops short of stating when NOT to use this tool (e.g., when you already have a concept ID), but the downstream routing is strong enough for an agent to infer the intended workflow.

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