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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds two useful facts beyond the annotations: the catalogue is exhaustive ('including tools not listed at this front door') and entries carry input schemas. It says nothing about result size, ordering, or whether the keyword matches names or descriptions.

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 purpose is front-loaded, but it is followed by a single sprawling parenthetical enumerating every server, dataset and sub-tool the catalogue returns — content the tool itself will hand back on invocation. This is padding, not orientation, and it buries the one actionable sentence at the very end.

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 one-optional-param, read-only discovery tool with no output schema, the description conveys the essentials: it covers all servers, it is exhaustive beyond the front door, entries include input schemas, and results feed into call. Missing only the return shape (fields, ordering) and the filter's matching rule.

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 100% and the schema itself gives an example ('regression, exam, npm'). The description only restates 'Optional query filters by keyword,' adding no matching semantics (name vs description vs server) or behavior on zero matches. Baseline 3 is correct when the schema does the work.

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 opening clause states a specific resource and scope: 'Every tool across all Data Butler servers ... with input schemas.' That is a clear discovery/catalogue purpose, and the closing line ('Run any of them with call') implicitly separates it from the execution sibling call. The mass of enumerated content dilutes the signal but the purpose is unambiguous.

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?

Usage is only implied: 'Run any of them with call, or connect to serverUrl directly' tells the agent what to do with the results, not when to reach for this tool versus coverage, what_changed_since, or the domain-specific lookups. No exclusions or alternatives are named for the discovery step itself.

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