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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description usefully adds that the skill never self-executes, grants permissions or publishes, plus the side effect of creating Personal Space when needed. That goes meaningfully beyond the annotations. It does not state what happens on a name collision or whether an existing skill is overwritten.

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?

Three short sentences, front-loaded with the action and artifact, then the authoring rule, then the safety/scope boundaries. Nothing is wasted; 'O++ metadata' is the only slightly opaque phrase, but it does not bloat the text.

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 6-parameter write tool with an output schema, annotations, and a Personal-Space default, the description covers the core mechanics well. However, source_refs is never mentioned despite being a structured provenance array with credential-safety constraints, and overwrite/duplicate-name behavior is unaddressed — both are gaps an agent would want closed before calling.

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 50%, so the description must carry weight, and it does: 'Supply only the procedure's Markdown body as instructions; frontmatter is generated from name, description and O++ metadata' clarifies the instructions/name/description contract in a way the schema cannot. It also clarifies space_id's default-to-Personal behavior. It says nothing about idempotency_key or the source_refs provenance array, leaving two parameters to the schema.

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 opening sentence gives a specific verb ('Save'), resource ('a reusable procedure'), and target artifact ('private SKILL.md'), which clearly separates it from skill_get/skill_list. It does not explicitly contrast with skill_update, but the word 'private' plus the creation framing make the intent legible.

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 through the instructions-authoring guidance and the 'never runs itself, grants permission or publishes' boundary, but there is no explicit statement of when to call this versus skill_update for an existing skill, nor any prerequisite/auth guidance. The agent must infer the create-vs-update split from sibling names alone.

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