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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, and the description adds meaningfully beyond them: an auth requirement ('Requires workflows:read'), a no-model-invocation guarantee, and a safety warning that source material is untrusted data. These are exactly the kind of behavioral traits annotations cannot express.

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 short, front-loaded sentences with no filler; the core purpose and the critical constraints (auth, untrusted data, execute only next_step) appear early. Telegraphic style is efficient, though the density borders on terse.

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 single-parameter read-only tool with no output schema, the description covers return content (draft/next step/checkpoint digest), auth, safety, and invocation context. The main gap is any explanation of session_id semantics.

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?

There is one parameter (session_id) with 0% schema description coverage, and the description never mentions it or explains its format/scope. With low coverage the description is expected to compensate, and it fails to do so.

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 (read) and resource (retained external draft, next step, or checkpoint digest) with a clear triggering context (after reconnect/restart). This distinguishes it implicitly from start_external_workflow and review_external_workflow, though no sibling is named 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?

Provides a clear usage condition ('after reconnect/restart') and an actionable directive ('Execute only the returned next_step'). It does not name alternative tools or when-not-to-use, but the context for invoking it is unambiguous.

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