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

Beyond the readOnly/idempotent annotations, the description discloses substantial behavior: superseded runs never request answers or approval, pending runs may lack a tracker entry, screening requires a current review version with offered choices, and the tool never retries or sends an application. These are exactly the non-obvious traits an agent needs.

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?

Purpose is front-loaded in the first clause, and each following sentence carries distinct operational information. It is a dense, list-like block rather than flowing prose, but there is little pure filler.

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 an output schema present, return values need not be described, and the description instead covers the edge cases that matter: missing tracker entries, screening prerequisites, superseded runs, and the review_url handoff. An agent has everything needed to call it correctly.

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 already 100% and states the either/or rule, so the baseline is 3. The description adds meaning beyond the schema by tying run_id/application_id to list_applications as the source and noting that a run_id may correspond to a pending run with no tracker entry yet.

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 ('Read') plus a precise resource ('one of your application tracker entries') and enumerates exactly what is attached (latest run, masked answers, parked questions, saved screening choices, next action). This single-entry read is clearly distinguished from the list sibling it sources IDs from.

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?

'Use exactly one application_id or run_id from list_applications' establishes the ID provenance and the mutual-exclusivity rule. It gives clear context for invocation but does not spell out when an agent should prefer this over list_applications or get_job.

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