office_get_review_image

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds two things annotations don't: the return channel ('MCP image content') and a validation behavior ('Rejects stale or changed evidence'), which tells the agent calls can fail on outdated input.

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?

Two tight sentences with no filler; the core action is front-loaded and each clause (preview coverage, stale rejection) earns its place.

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?

No output schema exists, but the description states the return is MCP image content and discloses the stale-evidence rejection, which covers the main unknowns for a 2-param read tool. It relies on the reader inferring the prior render/manifest workflow, which keeps it just short of fully self-contained.

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 50% - manifestPath is documented in-schema while unit only has a pattern. The description's 'one ... slide' weakly maps to the unit selector and 'evidence' loosely evokes the manifest, but it adds no syntax, format, or identifier semantics beyond the schema. Baseline 3 fits this partial coverage.

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 (Return) and resource (one previously rendered PowerPoint slide as MCP image content), plus the scoping nuance that it covers slides omitted from the initial inline preview. It is distinguishable from render/inspect siblings but does not name them 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?

The phrase 'slides omitted from the initial inline preview' implies when this tool is needed, and 'Rejects stale or changed evidence' hints at a precondition. But it never names an alternative (e.g. powerpoint_render_presentation) or states explicit when-not conditions, so usage is implied rather than spelled out.

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