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

With no annotations, the description carries the whole burden and does substantial work: it discloses data staleness ('snapshot refreshed every 15 minutes'), a non-obvious filtering behavior ('Servers that miss a role hardware or price floor are not listed for it'), and an assumption baked into results ('Fibre verdicts assume the launch-minimum stake'). It does not cover pagination behavior or whether any auth is required, which keeps it short of a 5.

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 purpose and filtering capability, and most sentences carry load (staleness, exclusion quirk, role/verdict coupling). It is dense and long, with minor duplication of the schema's mode definition and the provider-count figure, but no sentence is truly wasted.

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 16-parameter, no-output-schema, no-annotation tool, the description supplies the domain context an agent needs: what a verdict means, the two mode envelopes, FDP rules, snapshot freshness, and sibling routing. Pagination and return-shape expectations are the main gaps, tolerable given limit/offset defaults live in the schema.

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 81% (baseline 3), and the description adds real meaning on top: it explains the mode trade-off, that verdict semantics drive the role filter, and the caveat that Fibre verdicts assume launch-minimum stake, directing the agent to size_fibre_node for a specific size. The remaining un-annotated params (limit, offset, min_ram_gb) are only covered by the generic 'filter by... hardware' phrasing.

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 ('Browse rentable bare-metal servers for Celestia nodes... from the Unity Nodes Pulse datacenter catalog') and enumerates the returned dimensions (price, stock, location, CPU, RAM, NVMe, uplink, traffic, verdict). It explicitly differentiates itself from get_datacenter_offer and list_datacenter_providers, so an agent can route without opening a schema.

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 scope boundaries ('Celestia node hosting only, not a general server search and not a quote') and names both alternatives with their selecting conditions ('Use get_datacenter_offer for one server and list_datacenter_providers for the provider overview'). Nothing about when to pick this tool is left to inference.

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