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

Annotations already declare this is a non-read, non-destructive, closed-world write, and the description adds real value on top: the owner incurs ordinary Space usage (a billing consequence), and the operation is explicitly scoped to persistence only — no agent launch, curation, publication, or execution. What it omits is the idempotency/retry contract despite an idempotency_key being required.

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?

Two sentences, zero filler, with the core action front-loaded before the boundary conditions. Every clause carries distinct 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?

The output schema and annotations relieve the description of return-value and safety detail, and the purpose/boundary statements are solid. But for a 6-parameter write with four required fields and a nested provenance structure, silence on idempotency_key and source_refs leaves a meaningful gap for correct invocation.

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?

Top-level schema description coverage is 0%, so the description carries the burden and largely fails: only space_id ('the selected Space') and instructions ('exact SKILL.md') are obliquely implied. The required idempotency_key and the source_refs evidence array (up to 8 items, credential-free URI/excerpt provenance rules) get no mention at all.

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 and resource — 'Save an exact private SKILL.md in the selected Space' — which an agent can distinguish from private_skill_get/list/update by the verb alone. It does not explicitly name a sibling, but the create-vs-read/update distinction is unambiguous.

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 clause 'this does not launch an agent, curate, publish or execute the skill' usefully rules out a class of mistaken expectations about what creating a skill accomplishes. However, it never routes the agent to the actual alternatives (private_skill_update to modify, private_skill_get to read back, private_skill_list to discover), so when-to-use-vs-sibling is only implied.

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