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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered. The description goes further by disclosing the concrete content the agent will get back — availability state, human-start procedure, jail, persistent /work and limits — which is real behavioral context beyond the annotations. It does not explain pagination or response shape for result_offset.

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?

A single dense sentence that is front-loaded with the verb and resource, with zero filler. The enumeration of returned content is efficient, though the clause 'how to ask a human to start it' is slightly awkward to parse inline.

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?

There is no output schema, so the description correctly spends its words enumerating what is reported (availability, start procedure, jail, /work, limits), which is what an agent needs before calling the other executor tools. The main omission is any explanation of the pagination parameter, leaving a small gap for a two-parameter tool.

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% for two parameters, so the description must carry the burden and it does not. It never explains project_id nor, more importantly, result_offset, which is clearly a pagination control implied only vaguely by the word 'limits'. An agent must guess at pagination semantics.

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 opens with a specific verb and resource ('Describe the workspace executor for this project') and then enumerates exactly what is reported: availability (executor.available, state), how to request a human to start it, the sandbox jail, its persistent /work, and its limits. It also implicitly separates this discovery tool from the action-oriented executor siblings (executor_run, executor_job, executor_ssh_*).

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?

'Read it before using the other executor tools' gives an explicit ordering rule and points at the alternative family (executor_run, executor_job, executor_targets, etc.). It stops short of naming individual siblings or stating when-not to use it, but the sequencing guidance is clear.

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