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

Adds real context beyond the annotations: the artifact produced (a managed dataset.md version), that publication state is unaffected until publish_base, that base/document limits apply, and that there is no separate fee. What it omits is the behavior the destructiveHint implies — whether re-saving replaces a previously saved description — which matters given idempotentHint=true.

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 and the non-fetch caveat are front-loaded, and most sentences carry distinct operational information. The closing sentence about metadata and public discovery fees is the weakest — it is commercial reassurance rather than invocation guidance — but it is short and does not crowd out the substance.

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 an eight-parameter mutation with no output schema, the description covers the semantic model and lifecycle well but says nothing about what is returned on success or what happens to a pre-existing saved dataset description. Those are exactly the gaps an agent must know before invoking it, and they are not recoverable from the annotations.

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%, so all eight required parameters are documented in the schema, including the self-declared nature of license and update_frequency. The description adds no parameter-level guidance of its own (e.g., which fields matter most, or the significance of source_url being origin-only). Baseline 3 applies when the schema does the heavy lifting.

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?

A specific verb and resource ('Store a dataset description in your own base') plus an explicit scope limit ('The server does not fetch the source or import its data'), which separates it from connect_base_source and add_base_document. It also names the downstream partner tool (publish_base), so the agent knows this is a draft-staging operation.

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 establishes the workflow position clearly: save now, publish later, with publication untouched in between. It implicitly excludes fetching/importing behavior. It never explicitly names a sibling tool as the alternative for the cases this tool does not cover (e.g., connect_base_source for actual ingestion), so the exclusion is inferred rather than stated.

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