catalog_drop

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

With no annotations, the description carries the full burden and does disclose the key behavioral fact that tar files survive the deletion, plus the confirm gate. It does not say whether the drop is reversible, whether dependent catalogue rows (e.g. index entries) are affected, or what permissions/authority are needed for a destructive operation. That is meaningful partial disclosure, not complete.

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?

Single sentence, front-loaded with the action and its scope, zero filler. The colon-joined clauses compress the target audience, safety constraint and preconditions efficiently, though the phrasing is slightly telegraphic.

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?

For a destructive two-parameter tool with no annotations and no output schema, the description covers the essential safeguards: what is removed, what is preserved, and the confirm requirement. It still leaves reversibility and downstream effects on catalogue state unstated, which matters for a delete operation.

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 coverage is 50%: 'confirm' is already documented in the schema with the same meaning, so 'Requires confirm:true' largely repeats structured data. For the undocumented 'set' parameter the description only implies it identifies the set whose rows are dropped, adding modest meaning (it is a set, not a path or ID format). Around baseline given the coverage split.

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 a specific verb and resource ('Deletes a set's rows from the catalogue') and immediately bounds scope with '(not its tar files)', which prevents the most likely misreading of a destructive-sounding name. It also names the intended contexts ('test sets and re-packs'). It stops short of naming a sibling, so it is clear but not sibling-differentiated.

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?

'for test sets and re-packs' is a real hint about when this applies, and 'Requires confirm:true' is a stated prerequisite. But there is no explicit when-not guidance and no routing to alternatives such as catalog_restore or catalog_migrate for other catalogue operations, leaving the agent to infer the boundaries.

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