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

Beyond annotations (readOnlyHint, openWorldHint, idempotentHint), the description discloses the row limit (up to 50000 rows), constrains to a single catalog, and describes the input as a 'numeric constraint expression'. It also clarifies that it returns data rows, not metadata or summaries. 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 two sentences, front-loaded with the action and service, then adds limit and purpose. Every sentence contributes value without redundancy or fluff.

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?

The description covers the essential aspects: catalog ID, row limit, column selection, constraint, and the nature of the data. With an output schema present and strong annotations, it does not need to explain return format or safety. Minor gaps like how constraints are parsed are covered by schema examples. Overall, sufficient for a read-only query tool.

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 description adds meaning to parameters beyond the schema. It explains the catalog parameter as a VizieR ID with an example, describes columns as 'column selection', and defines constraint as a 'numeric constraint expression' and 'cut'—more informative than the schema's 'Solr-style constraints'. The schema covers most parameters, but the description compensates for the undocumented 'catalog' field.

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 the tool's purpose: 'return data rows from one published catalogue' via the VizieR service. It specifies the resource (VizieR astronomical catalogue service at CDS Strasbourg) and the action (query by catalog ID), distinguishing it from sibling tools like cone_search or catalogs by focusing on row extraction from a known catalog.

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 when to use the tool: when you have a VizieR catalog ID and want rows of objects meeting a constraint. It also mentions the optional column selection and constraint expression, implying use cases like filtering by numeric parameters. It does not explicitly exclude alternatives or mention sibling tools, but the guidance is sufficient for typical usage.

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