Update a project

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

Annotations only declare readOnly=false, idempotent=true, destructive=false. The description adds behavior the agent could not otherwise know: null clears a field, a list replaces the entire list, contact_email is immutable post-launch, and after launch an edit only propagates to listings not yet sent to a directory. That last point is a genuinely non-obvious partial-propagation effect that directly affects how a caller reasons about the result.

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 compact sentences, front-loaded with the update semantics and then the launch-state constraints. Every clause carries distinct information: partial send, null-clears, list-replaces, immutable field, and post-launch propagation scope.

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 22-parameter mutation tool with an open-world annotation and no output schema, the description covers the semantics that matter most: how to send fields, what clears data, and what is forbidden after launch. It does not say what the response contains or how errors are surfaced, which leaves a small gap for a mutation with this many fields.

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 already 82%, so most parameters are self-documenting. The description still adds cross-field semantics the schema only states piecemeal (replacement for tags, competitors, metadata, excluded_directories): a uniform rule that null clears and lists replace wholesale, plus the immutability of contact_email. Enum values for category, pricing_model, and price_period remain only in 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?

States a specific verb and resource: 'Changes project fields.' Combined with the name update_project, an agent immediately understands this is a partial-update operation on a single project. It does not explicitly contrast with siblings like create_project or get_project, but the mutation/read distinction is unambiguous from the verb.

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?

"Send only what changes" tells the agent to use this as a PATCH-style call rather than a full replacement, and the launch-state caveats ("contact_email cannot change after launch") tell it when an edit will fail. There is no explicit pointer to an alternative tool when the edit is rejected, but the preconditions are clear.

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