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

With no annotations present, the description carries the full behavioral burden, and it delivers: it explains that a connector can swallow errors and still return ok:true, that empty/zero data can look legitimate, that authentication failures may only be visible here, and the platform/HTTP limitation. This goes far beyond what the schema alone communicates.

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?

The description is longer than typical, but the extra length earns its place: the core statement is front-loaded, the real-world case makes the failure mode concrete, and the usage/limitation guidance is actionable. Slight redundancy such as emphasizing 'only place' twice could be tightened, but it remains well organized and purposeful.

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 debugging/log-reading tool with no annotations and no output schema, this description covers what an agent needs: what the tool does, when to reach for it, how to use the cursor for incremental reads, and which connector types are unsupported. The only minor omission is an explicit return-shape description, but the references to 'returned cursor' and stderr lines provide enough context.

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 coverage is 100%, so the baseline is 3. The description adds genuine value beyond the schema by explaining the cursor workflow: 'Pass the returned `cursor` back as `since` to read only what is new since your last look, so you can bracket an action.' This clarifies the intended use of `since` in a way the schema does not.

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 opens with a specific verb and resource: 'Read what a connector process actually PRINTED to stderr.' It clearly distinguishes this from generic logs or execution logs by explaining that this is the only place an internal connector failure becomes visible, and even contrasts it with tools that return ok:true despite failures.

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 description gives explicit when-to-use guidance: 'USE IT whenever a tool succeeds but the data is empty, wrong, or zero — that combination is the signature of a swallowed error.' It also states when NOT to expect this to work: 'Only stdio (solution) connectors stream stderr through Core; a platform/HTTP connector answers ok:false with a reason.' This clearly routes the agent.

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