Delete a skill

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

Goes well beyond the destructiveHint annotation by disclosing authentication requirements (OAuth only, API key refused) and the precise blast radius of deletion (git-imported skills are removed from Orchestra but the repository file is untouched). This is exactly the side-effect context an agent needs before calling a destructive tool.

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?

Four front-loaded sentences: the action first, then the three constraints that matter. Every sentence carries a distinct rule with no repetition or filler.

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 tool with no output schema, the description covers the prerequisites (OAuth), the blocked cases (Orchestra-managed skills), and the resulting state change (repo left intact), which is everything an agent needs to call it correctly.

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 100%, so both skill_id and X-Orchestra-Account-Id are already documented in the schema. The description adds no syntax or format guidance, so the baseline of 3 applies.

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 ('Delete a skill') that is unambiguously distinct from create_skill, update_skill, get_skill, and import_skill. It doesn't explicitly name a sibling or contrast its scope, but the destructive verb leaves no ambiguity about intent.

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?

Provides clear when-not conditions: skills managed by Orchestra cannot be deleted, and the tool is refused under API-key auth, running only for OAuth sessions. It doesn't name alternative tools for those blocked cases, keeping it short of the top band.

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