check_deliverable_status

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

Annotations already cover read-only/idempotent safety, so the bar is lower. The description adds real value beyond that: polling cost (free), expected duration (a few minutes), recommended cadence, and the possible status values with artifact links on completion.

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?

Front-loaded purpose, then parameter sourcing, then return behavior and cadence, closing with a short parenthetical label. Every sentence carries usable information with no padding.

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?

Although no output schema exists, the description enumerates the return contract (status enum plus artifact links on completion) and the polling behavior, so an agent can act without further inference.

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% and the description's guidance ('Pass the job_id from that response') duplicates what the schema already states for job_id. No additional syntax or format detail is added, so the baseline 3 is appropriate.

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 states a specific verb+resource ('Poll a deliverable') and immediately names the sibling that produces the job_id ('commissioned with request_deliverable'). This clearly separates it from other status-check siblings like check_research_status and check_supplemental_status.

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 says when to use it (after commissioning via request_deliverable) and gives operational cadence ('poll every ~15–30s'), plus the fact that polling is free. It stops short of stating when not to use it, but the contextual routing is clear.

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