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

Goes well beyond the readOnly/idempotent annotations: it states the call does not spend credits, that images over 5 MB are refused, that retention-window deletion produces a failure naming the deletion time, and that other users' private sessions are inaccessible while public sessions are readable by id. These are exactly the operational constraints an agent cannot infer from the schema.

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?

Four sentences, each carrying a distinct load (output form, argument provenance, cost/size limits, failure and access rules), with the core action front-loaded. No redundancy or 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 two-parameter read tool with no output schema, the description covers the return type (an MCP image), the credit/size economics, and the two realistic failure modes. Nothing needed to invoke it correctly is missing.

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 only 50% (sessionId has a trivial "Session ID" note; fileName is undocumented). The description compensates by explaining where each value comes from — the run's sessionId and the filenames emitted by get_run — which is meaning the schema does not carry.

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 ("Return one screenshot from a session as an MCP image") with concrete scope: a single screenshot, streaming back as an image rather than metadata. It also implicitly separates itself from get_run, which only lists file names.

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 clear prerequisites and provenance for both arguments: sessionId from the run, fileName from the names get_run lists. That is actionable routing between this tool and its sibling. It stops short of an explicit when-not-to-use statement, but the context is unambiguous.

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