yc_register_operation

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

Annotations declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, and the description is consistent with them while adding real context: persistence is local-only, execution is deferred, and existing names require explicit replacement (explaining the replace flag's effect). The secrets/variables guidance is a genuine behavioral constraint not captured by annotations. It stops short of saying how collisions are reported or where documents are scoped.

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?

Three short sentences, front-loaded with the purpose, followed by safety guidance and the replacement condition. No filler, no restatement of the title, every clause carries information.

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?

An output schema exists, so return values need not be described, and the mutation-safety profile is carried by annotations. The description covers purpose, safety, and replacement behavior. Minor gap: the undocumented description parameter and the scope of the local store (per application vs. global) are unaddressed.

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 0%, so the description carries the full burden, and it only partially compensates. It explains the replace semantics and implies operationName ('existing names'), but never mentions the description parameter, the name pattern/maxLength limits, or what form 'query' should take. Roughly half the parameters gain meaning from the prose.

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?

Specific verb plus resource: 'Persist an observed named GraphQL document locally, without executing it.' The negative clause ('without executing it') distinguishes it from yc_run_operation, though no sibling is named explicitly. An agent can tell what the tool does at a glance.

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 implied: register a document rather than execute it, and use variables rather than inlined values. There is no explicit statement of when to prefer this over yc_run_operation or yc_prepare_mutation, and no prerequisites or lifecycle context. Adequate but leaves the agent to infer the routing decision.

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