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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real behavioral context beyond them: output is bounded, may contain sensitive content, and the call requires account-bound computer:write OAuth plus possible local owner approval — an auth prerequisite 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?

Three tight sentences with the core action front-loaded and no filler; the sensitivity warning and auth requirement are each stated once. The phrase 'using its session ID and offset' mildly duplicates the schema, which keeps it short of perfect.

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 with no output schema, the definition covers action, alternative, sensitivity, and auth prerequisites — enough to call it correctly. The remaining gap is what 'bounded' means in practice (truncation limits, whether offset continues past the bound), which an agent must discover empirically.

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 100%, and both parameters are documented there, including the 'use returned continuation data' hint for offset. The description restates the two inputs but adds no format, units, or cursor semantics beyond what the schema already provides, so the baseline of 3 applies.

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 ('Read bounded stdout/stderr from an EXZA interactive process') plus the scoping mechanism ('using its session ID and offset'). It also explicitly separates this tool from the closest sibling, exza_get_background_job_status, so an agent can route without opening a schema.

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 an explicit alternative for the most likely confusion: job output goes to exza_get_background_job_status instead. It does not cover other adjacent cases, such as when to list processes first (exza_list_interactive_processes) or when to send input instead, so the guidance is clear but not exhaustive.

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