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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: which intermediate statuses mean 'keep polling,' which are terminal, and what a successful payload contains (final resource URLs, and count as actually charged credits). Billing semantics and polling cadence are exactly the kind of context annotations cannot express.

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-loads identity in one sentence, then sequences the operational instructions in logical order: poll once only, initial wait, backoff ladder, stop conditions, result shape. Every clause is actionable and none is redundant.

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 no output schema, the description correctly compensates by describing return values and terminal statuses, and it fully covers the polling loop. Minor gaps remain: what to do after TIMEOUT (retry, abandon, re-generate) and whether the taskId expires or polling incurs further credit charges.

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 both parameters carry strong descriptions, including the notable 'Never invent or replace this value' warning, so the schema already does the heavy lifting. The tool description adds no parameter-level detail beyond referring to 'a previously created task'; baseline 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: 'Query a previously created Nexscope media-generation task,' which clearly positions it as the polling companion to the generation tools rather than a generator itself. It never names the specific sibling generation tool or distinguishes itself from nexscope_seo_call_result, so sibling differentiation is implied from context rather than explicit.

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 explicit sequencing ('Call the generation tool only once'), a minimum delay before the first poll (5 seconds), a concrete backoff schedule (5, 10, 20, then 30 seconds), and precise termination conditions (SUCCEEDED, FAILED, TIMEOUT). This is a complete when/how-to-invoke protocol with no inference required.

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