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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), and the description layers on real behavioral context: authorization is mandatory, contributions are revocable, and per-item submission preserves isolation of routing, duplicate detection, verification, and revocation. It omits failure behavior and what happens after submission, keeping it from a 5.

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, front-loaded with the trigger condition and the authorization gate. The second sentence is dense but each clause earns its place by establishing the one-item-per-call contract and the prohibition list.

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 complex nested write with no output schema and a 0% documented schema, the description supplies the essential calling rules: prerequisite call, authorization, cardinality, sanitization, and revocation. It stops short of explaining what a successful submission returns or how verification/duplicate outcomes surface, which would be useful given the schema depth.

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 0% and the schema is a deep nested object, so the description must carry the full load. It maps the two top-level parameters implicitly ('one skill item with its single-use receipt') and reinforces the consent/privacy constraints ('revocable, sanitized', 'never include...'), but leaves nested structures like protocol_version, source_agent, invocation, and reusable_steps unexplained.

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 action (submit exactly one skill item) on a specific resource (reusable, sanitized experience) and anchors it to a sibling by naming saash_grow_invoke as the prerequisite. An agent can distinguish this from saash_gateway_discover, saash_grow_invoke, and saash_resolve 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 defines the trigger condition ('after a successful saash_grow_invoke call') and the gating requirement ('the user explicitly authorizes a revocable, sanitized contribution'), plus the per-item repetition rule for packages. This is a when-to-use, precondition, and alternative-handling statement all in one.

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