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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description goes further with non-obvious behavior: omit-a-field keeps the value, an empty list clears, a non-empty list replaces without merging, commands/variables create a new revision while a name alone renames, and type is immutable. What is missing is any note on failure/partial-failure or permission requirements beyond confirmation.

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 purpose is front-loaded in the first clause, and every subsequent sentence delivers a distinct operational rule (optionality, clearing vs replacing, type immutability, revision behavior, read-before-write, confirmation). No filler or repetition.

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 partial-update, non-idempotent, destructive mutation with no output schema and a shallowly documented nested schema, the description supplies everything an agent needs to invoke it correctly: which fields are optional, what omission means, which operations create revisions, and the confirmation requirement.

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% and the schema is nested, so the description carries real burden and largely does: it explains the optionality and merge-vs-replace semantics of commands and variables and the immutability of type. It does not define the nested variable fields (dataSetId, selectionStrategy, updateStrategy) or state what projectId/scriptId identify, leaving some gaps.

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+resource ('Update an existing script') and immediately scopes it against siblings by explaining that a type change requires creating a new script rather than updating. An agent can distinguish this from create_script, duplicate_script, and import_script without opening any 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?

Explicitly prescribes the workflow: read with get_script before changing, never rebuild from list_scripts, and obtain explicit user confirmation before writing against existing data. It also names the correct alternative for an unsupported operation (create a new script to switch types).

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