gc_records

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It doesn't reveal whether delete/update are destructive to existing data, whether transitions mutate state, whether operations persist immediately, or what the response format looks like. Given that delete and transition are clearly mutating operations, their safety profile is entirely undisclosed.

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 efficient at 3 short sentences with a compressed telegraphic style. However, the final sentence ('Use params for Records query filters, sort, temporal constraints, and pagination.') is somewhat vague and the second sentence reads like terse shorthand. It's concise but sacrifices clarity for brevity; a touch more elaboration would improve value without bloating it.

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?

This is a complex 8-parameter tool with no output schema and no annotations covering 9 distinct actions. The description doesn't explain return values, error behavior, or which actions are read-only vs mutating. For a tool of this complexity, the 3-sentence description is insufficiently complete to guide correct invocation across the full action surface.

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 all 8 parameters have descriptions in the schema. The description adds value by explaining which params go with which actions ('Use definition for define_type', 'Use params for Records query filters'), which is genuinely helpful disambiguation beyond the schema. However, parameter-specific format details (e.g., what 'temporal constraints' look like, the pub_id format) are not elaborated.

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 states it covers 'Runtime record definitions and instances' with a clear verb+resource framing, and lists the 9 actions. However, it's a polyglot tool bundling many distinct operations (CRUD, type definitions, transitions), so the purpose is diffuse rather than a single specific task. The title is null and the description reads as a header for a family of actions rather than a tightly-scoped function.

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?

There's some guidance ('Use definition for define_type and data for create/update', 'Use params for Records query filters') that maps actions to parameters. But there is no when-to-use guidance versus sibling tools, no exclusions, and no mention of when this tool is preferred over the many gc_* siblings. The action-specific usage hints are minimal and don't cover all 9 actions.

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