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

Annotations already cover the read-only/idempotent/non-destructive profile, yet the description still adds real context: unauthenticated access, the absence of pricing ('price lives on orders'), and a conditional behavior — fungible grades appear only while the token order book is on. That conditional listing rule is exactly the kind of nuance 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-loaded with the core definition, then the returned fields, then the cross-reference to sibling tools, then two caveats. The middle field enumeration (input_schema, output_schema in the scope DSL, acceptance_kinds, sla_seconds, unit) is dense and jargon-heavy, but every clause carries information rather than 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?

There is no output schema, so the description usefully enumerates the returned fields (id, slug, version, kind, title, description, schemas, acceptance_kinds, sla_seconds, unit). A few fields such as acceptance_kinds and unit are named but not explained, leaving minor gaps, but the agent has enough to call the tool and use the result.

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?

The tool takes no parameters, so there is nothing for the description to disambiguate; baseline applies. Nothing in the description misleads about inputs.

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 ('List Bitroad's grades') and immediately defines the domain term as 'the published contracts for classes of work that orders are placed against', so an agent unfamiliar with 'grades' still knows what it is retrieving. It is clearly distinguishable from siblings like catalog_list_categories or seller_list_listings.

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 concrete downstream usage: 'pass its id as grade_id to intents_post or services_create_listing', which names sibling tools and the exact parameter, plus the practical note 'Works without credentials'. It does not state explicit when-not-to-use conditions, but the context is clear enough for selection.

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