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

Despite annotations already declaring non-readOnly and idempotent, the description adds critical behavioral context beyond them: it returns request metadata rather than proof of an editor opening, and no local action occurs without a local agent. This async/fire-and-forget nuance is exactly what an agent needs and is not derivable from 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?

Three short sentences, each carrying distinct weight: the action, the return caveat, and the environmental dependency. It is front-loaded with the core purpose and has no filler.

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 mutation tool with no output schema, the description covers the most important gap by clarifying what the return value does and does not represent. It does not explain the roles of optional fields like details or sessionId/executionId, but those are covered by the schema, leaving only minor incompleteness.

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 schema itself documents all six parameters (including idempotencyKey retry semantics and nodeId discovery via get_roots/get_graph_scope). The description contributes no additional parameter meaning, so the baseline of 3 applies.

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 gives a specific verb and resource: 'Record a pending request to open a published graph node in the connected local editor.' It clearly frames the action as recording a request rather than performing the open itself, which is a meaningful distinction. It does not explicitly name a sibling tool, but the semantics are distinctive enough that an agent can separate it from neighbors like relay_execute_local_action.

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 is no explicit when-to-use guidance, no stated alternatives, and no prerequisites spelled out. The clause about a local agent only describes a failure mode, not when to prefer this tool over related ones like open_project_session or relay_execute_local_action. The agent must infer usage entirely.

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