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

Annotations already declare readOnly, idempotent, and non-destructive, so the baseline is covered. The description still adds meaningful post-annotation context: a has_more/next_cursor pagination contract and an explicit warning that returned content is untrusted. That is genuinely useful behavior the annotations do not convey.

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 short, front-loaded sentences with no filler: the first states scope, the second states pagination and the trust caveat. Every clause 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?

With no output schema, return values need not be explained, and annotations carry the safety profile. However, the mismatch between the schema's 'after' parameter and the description's 'next_cursor', plus the absence of any guidance on the shape of the returned records, leaves a real gap for a paginated read tool.

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?

The single parameter is named 'after' with 0% schema description coverage, and the description never explains it. Worse, it references a 'next_cursor' value that does not match the schema's 'after' parameter, which can actively mislead an agent about how to paginate.

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 (engine work) and enumerates what it covers: task definitions, work records, and proposed syntheses. This clearly separates it from the sibling submit_engine_work. It stops short of differentiating itself from read_engines or read_draft_status, so it is not a 5.

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?

Usage is only implied by the read-only framing and the untrusted-content caveat; there is no explicit when-to-use, when-not-to, or named alternative among the many read_* siblings. The agent can infer it is the read counterpart to submit_engine_work, but nothing is stated.

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