edits_invoke

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

Annotations already declare destructive/openWorld/non-idempotent, and the description adds genuinely new operational context: the allowlist gate, the env-var gate for writes, absence of automatic retries, and the instruction to inspect state after a timeout. These are exactly the failure and authorization traits an agent cannot infer from the annotations or schema.

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?

Five short sentences, front-loaded with the core action, then gates, then schema semantics, then failure handling. No filler; each sentence supplies a distinct operational fact.

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 dynamic dispatcher with no output schema and an opaque 'arguments' object, the description covers authorization, schema delegation, destructive potential and timeout semantics. What is missing is return-value shape and how the agent learns the per-tool native schema before constructing 'arguments'.

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 0%, so the description must carry the load, and it does: 'name' must be an exact native tool identifier sourced from edits_catalog, and 'arguments' is a passthrough governed by the native tool's own input schema. It still does not say whether the native schema is discoverable per entry or how to obtain it, which leaves a small gap.

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: invoke an exact native tool discovered via edits_catalog. The capability sentence ('Can edit, export, delete or publish...') defines the scope of what may be dispatched, which cleanly separates it from edits_catalog (discovery) and edits_status (state inspection).

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?

Gives concrete preconditions: operator allowlist required, and EDITS_ALLOW_WRITES=1 for write-style tools, plus post-timeout behavior (no automatic retries, inspect state). It does not explicitly say 'resolve the name via edits_catalog first' or what to do when a name is not allowlisted, so the alternative-selection guidance is implied rather than stated.

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