Publish Python metric draft

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: publishing targets an exact immutable draft by fingerprint, can revise an existing metric, and requires successful preview IDs. It still does not describe permissions, irreversibility, or what happens to the prior metric on revision.

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 three sentences, front-loads the core publish action, and every sentence adds useful information about fingerprint binding, revision behavior, or preview requirements. There is no redundant restatement of the tool name or schema.

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 destructive mutation with three required parameters and no output schema, the description gives enough to understand the core operation but not enough to execute confidently end-to-end. It omits where fingerprint and preview IDs come from, whether publish returns a metric identifier, and what the practical effect on an existing metric is beyond 'revise'.

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 only 33%, so the description must compensate for missing parameter details. It does clarify that the fingerprint identifies the exact immutable draft and that preview IDs must correspond to successful previews, but it does not explain how to obtain the fingerprint or preview IDs, nor does it describe preview_ids beyond the success constraint.

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 uses a specific verb and resource: 'Publish the exact immutable Python metric draft identified by its fingerprint.' It also clarifies that publishing can revise an existing metric when targeted, which distinguishes it from a pure creation operation. It does not explicitly name sibling tools such as create_python_metric_draft or create_python_metric_preview, so sibling differentiation is implicit rather than explicit.

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 sentence 'Supply only successful preview IDs for this draft' implies the tool should be used after successful previews exist, giving some usage context. However, the description never states when to use this versus create_python_metric_draft, create_python_metric_preview, or get_python_metric_draft, nor does it provide explicit exclusions or alternatives.

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