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

Annotations already declare the write/idempotent/non-destructive profile, so the bar is lower. The description still adds real behavioral context: datasetPolicy performs uniqueness/reference/count checks, validation 'is not vendor fidelity or independently verified import consent,' the tool never reads host paths, and it returns retained IDs/digests and validation metadata rather than source. Side-effect boundaries (no instance allocation, no agent execution) are also disclosed.

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?

Purpose is front-loaded in the first sentence, followed by compact clauses on policy, metadata, validation caveats, path scope, and return shape. The jargon is dense but each sentence carries distinct information; only the string of negative caveats borders on 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?

Given a complex polymorphic schema and no output schema, the description covers purpose, both action modes, policy validation semantics, metadata scope, validation limitations, path isolation, and return contents. An agent has enough to select and invoke it correctly; remaining gaps are minor per-field details already structurally encoded 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 description coverage is 0% and the single top-level parameter is a dense polymorphic request, so the description must carry semantics. It clarifies the two request shapes (service source vs seed dataset), the meaning of datasetPolicy constraints, and what dataset metadata records (provenance and version-pinned cross-dataset mappings). It is silent on several nested fields (entryPoint, files, buildId, environmentId), which the enum/const-driven schema documents structurally but without prose.

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 (Publish) and two distinct resources: 'private service source' and 'immutable seed dataset'. This maps cleanly to the schema's two request variants (build vs dataset). It does not, however, name or contrast any sibling such as firedrill_service_create or firedrill_service_invoke, so differentiation is left to inference.

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?

Usage is implied rather than stated: 'Never reads host/repository paths' and 'Does not allocate an instance or run an agent' implicitly bound what this tool is not for, which helps contrast it with allocate/run-style siblings. But there is no explicit 'use this when… instead of X' guidance and no prerequisites or preconditions named.

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