Process output

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

With no annotations, the description carries the burden and does disclose two behaviors an agent needs: ordering ('newest last') and the seq-based incremental retrieval mechanism. It omits whether output is bounded/truncated and whether the call blocks, which are relevant for an output-retrieval tool, but the core behavioral traits are present.

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 sentences, front-loaded with what is returned, followed by the ordering guarantee and the incremental-retrieval hint. No filler, every clause carries information.

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 4-parameter, no-required, no-annotation, no-output-schema read tool, the description covers content, ordering, and return shape (lines with seq), which substitutes for the missing output schema. The remaining gaps are limit defaults and truncation/buffering behavior.

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 only 50%: grep and since_seq are documented in the schema, while source (an enum) and limit are not. The description restates since_seq semantics but adds nothing for grep, source, or limit, so it does not compensate for the coverage gap.

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 names a specific resource (process output) and enumerates exactly what is captured: stdout, stderr, console.* calls, and uncaught exceptions. That enumeration distinguishes it from siblings like get_stack, get_scopes, and get_properties without needing to name them.

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?

It gives one concrete usage pattern, 'pass since_seq to get only new lines,' which implies incremental polling. But it never states when to call this versus alternatives, nor any exclusions or prerequisites (e.g., whether the process must be paused/running), leaving usage largely inferred.

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