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

Annotations provide destructiveHint: true, and the description reinforces this with a prominent 'MUTATES Parabol data (potentially)' warning. It also discloses the escape-hatch nature, the endpoint, and token-scope requirements, adding context beyond the annotation. It does not contradict the 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 compact and front-loads the most important behavioral warning ('MUTATES Parabol data (potentially)') before explaining purpose and usage. The phrase 'including any mutation' is slightly redundant with the mutation warning, but overall every sentence serves a clear function.

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 an arbitrary GraphQL escape hatch with no output schema, the description supplies the endpoint, variable support, authentication expectation, mutation warning, and routing guidance. It is not missing information an agent needs to decide whether to call it or how to invoke it safely.

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%, with query and variables already documented in the input schema. The description adds only that variables are 'optional' and that the operation can be a query or mutation, but this does not materially expand on the schema. Baseline 3 is appropriate.

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 identifies a specific action ('run an arbitrary Parabol GraphQL operation') and resource ('action.parabol.co/graphql'), including explicit mention of mutations. It clearly distinguishes itself from curated tools and names the sibling parabol_query for read-only calls, so an agent can tell them apart.

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 explicitly states when to use this tool: 'Use for operations not covered by the curated tools.' It also gives a clear exclusion: 'Prefer parabol_query for read-only calls,' and warns that the token must carry the required scope. This is direct, actionable guidance with an alternative named.

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