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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, but the description adds substantial context: it reads precomputed published data, does not fetch upstream or create evidence, and describes a bounded artifact not representing semantic truth, completeness, certification, legal permission, safety, or AI admission. It also discloses DataPulse is read-only, needs no API key, and is rate-limited to roughly one request per second with a burst, giving the agent realistic expectations beyond the structured annotations.

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?

The description is longer than typical, but every sentence earns its place: core action, artifact scope, semantic limitations, alternative tools, and rate-limit guidance are all distinct, non-redundant facts. It is front-loaded with the primary purpose and then layers caveats in a logical order, though it could be slightly tightened without losing information.

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 the tool's complexity, the description is thorough: it specifies the artifact version, what the passport describes and does not describe, the exact meaning of evidence_available=false, authentication and rate limits, and clear routing to sibling tools. The output schema exists, so return values need no description, but all other operational context required for correct invocation is present.

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 input schema has 100% coverage, including a detailed description of dataset_id as a stable slug returned by search_datasets, an example, and the requirement that it must be a slug rather than a display name. The description calls it a 'canonical dataset ID' but adds nothing beyond that; the schema already carries the semantic weight. Baseline 3 is appropriate.

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 begins with a specific verb and resource: 'Return one bounded, machine-readable Dataset Passport v1 for a canonical dataset ID.' It also distinguishes itself from siblings by explicitly stating it 'reads the published Passport artifact only; it does not fetch an upstream source or create evidence' and contrasts with 'get_dataset or get_provenance'. This leaves no ambiguity about the tool's function.

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?

The description gives explicit when-to-use and when-not-to-use guidance: 'Use it for the bounded Passport artifact; do not use it for current health detail or citation context—use get_dataset or get_provenance instead.' It further clarifies the semantics of evidence_available=false and rate-limit behavior, so an agent can decide when to invoke it and what to expect.

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