Get a dub

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and external reach are covered. The description adds genuine value by enumerating the terminal and in-flight states (queued, processing, completed, failed) and the presence of stage, progress, and a failure error — effectively a return-shape contract in the absence of an output schema. It says nothing about whether the call fetches live from a provider, whether staler cached data may be returned, or how an agent should poll.

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?

One compact clause listing only the fields that matter, front-loaded with the primary status value. It is a fragment without a verb, which slightly hurts readability, but there is no redundant or padded wording to remove.

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 single-parameter read with annotations covering the safety profile, this is nearly sufficient: the agent knows what comes back. What is missing is operational context an agent needs to use it well, namely the relationship to wait_for_dub / list_dubs for waiting and enumeration, and any note on error behavior for an invalid id.

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 single dub_id parameter is documented in the schema with a format example (dub_…). The description adds no meaning beyond that — no id provenance, no behavior for unknown/malformed ids. Baseline 3 is appropriate when the schema carries the parameter burden.

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 is a noun phrase enumerating the returned fields (status, stage, progress, error) for a single dub, so the resource and payload are identifiable, but it supplies no verb of its own and relies on the title 'Get a dub' plus the schema to convey that it retrieves by id. It implicitly contrasts with list_dubs by speaking of 'a dub' rather than many, but never states that differentiation.

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?

There is no when-to-use guidance at all: nothing tells the agent to call this for a one-off status check versus using wait_for_dub to block until completion, or how it relates to list_dubs for bulk status. The reader must infer that this is the polling primitive from the field list alone.

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