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), so the description is free to add what they cannot: that this is a prerequisite step before mutating actions and that the data can go stale, requiring a refresh. It stops short of describing the returned shape (e.g. how capabilities are enumerated) or error behavior on an invalid workspaceId.

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 imperative sentences, each earning its place: what it reads, the constraint against role-name inference, and the refresh trigger. The most important instruction sits first with zero preamble.

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 two-required-param, no-output-schema read tool, the description covers purpose, timing, and staleness — enough to invoke it correctly. A small gap remains: it doesn't say whether the returned 'commandVersion' must be passed to subsequent write tools, which would matter for an agent chaining calls.

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% and both parameters already carry the strong 'exact ID returned by a Company tool; never a personal platformId' guidance plus a 24-hex pattern. The description adds no additional parameter meaning, so the baseline 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 names a specific verb ('Read') and a specific resource ('one Agency Workspace's current role capabilities and commandVersion'), which is far more precise than the title's restatement. It implicitly separates itself from account/ownership siblings by scoping to a single workspace's role capabilities, though it never names a sibling tool explicitly.

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 gives real usage conditions: read this 'before acting', refresh 'after a conflict or workspace change', and the explicit anti-pattern 'Never infer permissions from a role name'. That is strong temporal guidance, but no alternative tool is named as a fallback or contrast point.

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