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

Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context beyond that: mutations are actively rejected, the query is sent to action.parabol.co/graphql, and valid read scopes are required on the token. This goes beyond the structured annotations without contradicting them.

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 appropriately sized and front-loaded with the escape-hatch framing. Every sentence contributes a distinct piece of information, though the first sentence somewhat repeats the title's read-only claim, which is already present in the annotation title.

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 flexible escape-hatch tool with two parameters and no output schema, the description covers the essentials: endpoint, parameter shape, rejection of mutations, alternative routing, and auth requirements. A brief note on standard GraphQL response formatting would be a minor addition but is not necessary for correct invocation.

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 the baseline is 3. The description reinforces that variables are optional and that the query must be a query rather than a mutation, but it does not add significant syntax or format details beyond what the schema already documents.

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 names a specific verb ('run'), a resource ('arbitrary Parabol GraphQL query'), a target endpoint, and explicitly labels itself an 'escape hatch' for fields not covered by curated read tools. It also distinguishes itself from sibling tools by stating mutations are rejected and routed to dedicated write tools or parabol_graphql.

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?

It explicitly states when to use this tool ('Useful for fields not covered by the curated read tools') and when not to use it ('Mutations are REJECTED — use the dedicated write tools or parabol_graphql for those'). It also notes the token requirement for matching read scopes, providing clear selection guidance.

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