discover_collections

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals semantic search behavior ('Read all catalog entries by meaning; synonyms can have no shared words'), the workflow coupling ('Incomplete review cannot authorize creation'), and the fact that it returns a discovery_id. It does not state side effects or permission requirements, but 'Review' and 'Returns' strongly imply a read-only operation.

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 compact and front-loaded with the most important instruction. Most sentences earn their place, especially the semantic-matching note and the creation-authorization constraint. The final phrase 'do not ask routinely' is somewhat unclear and slightly undercuts the otherwise tight structure.

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 tool's purpose, output content, and workflow context, and an output schema exists so return structure does not need explanation. However, the required parameters are not adequately explained, and the relationship between discovery_id and create_collection is implied but not explicit. This leaves a notable gap for a tool meant to gate collection creation.

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 0%, so the description must compensate for the opaque `name` and `purpose` parameters. It hints that matching is semantic ('Read all catalog entries by meaning'), which likely relates to `purpose`, but it never explains what `name` represents or how it is used. This leaves an agent guessing about half the required inputs.

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 opens with a specific action and context: 'Review the existing catalog BEFORE collection creation.' It also enumerates the return payload ('full names, purposes, aliases, representative records and lexical suggestions, plus discovery_id'), making the tool's function concrete. It is clearly distinguished from siblings like create_collection and list_collections by its pre-creation discovery focus.

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 gives explicit timing: use it 'BEFORE collection creation.' It provides behavioral guidance to 'prefer reuse when purpose fits,' and notes that 'incomplete review cannot authorize creation,' signaling a prerequisite workflow. It does not name alternative sibling tools or explicitly state when not to use it beyond the slightly ambiguous 'do not ask routinely,' so it falls just short of a 5.

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