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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds cost and lifecycle context that annotations cannot: one metered execution per call, ~2 second inline return, otherwise retain IDs for operation_status/operation_output rather than resending. That is exactly the kind of behavioral detail an agent needs for scheduling and retry decisions.

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?

Front-loads the trigger condition, then prerequisites, then the result-handling rule, with no filler sentences. It is dense and runs long for a single paragraph, but each clause carries operational meaning (cost, timing, retry guidance).

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 complex tool (8 params, nested efficiencyProfile, no output schema) the description covers the return path: short result inline in ~2s or async IDs to poll. It stops short of describing what 'bounded summary' contains or what happens on timeout/failure, but the essential calling contract is present.

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 already documents path, taskId, startup, deadlineAt, idempotencyKey and efficiencyProfile. The description only restates sessionId provenance and operationId freshness, which the schema already says; it adds no new syntax or constraint detail. 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?

States a specific verb and resource (bounded summary of an approved project's files and Git state, plus policy/task continuation under startup). An agent can distinguish this from fs_list, git_status and git_diff because it is framed as a combined, bounded overview rather than a listing or diff.

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?

Gives a clear triggering condition ('when the user wants an overview of an approved project') plus hard prerequisites: sessionId from execution_session_open and a fresh operationId. It also routes long-running results to operation_status/operation_output and warns against resending, but it never names an alternative tool for the narrow case (e.g. plain file listing or git status), so no explicit exclusions.

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