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

The description adds far more than the annotations: it creates a DRAFT that is never published, shows that the user, not this tool, is responsible for publishing, includes a direct link in the response, resolves the location against a real area tree, and mentions the agency API key requirement. These are exactly the behaviours an agent needs to set expectations and act accordingly.

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?

The description is compact and front-loaded: the very first sentence states the core action and target system, followed by the relevant when-to-use context, the DRAFT caveat, and the key technical side (link, area-tree resolution, API key). Every sentence earns its place with no fluff.

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 create tool with 11 parameters and no output schema, the description covers almost all procedural essentials: the draft state, the link, the auth, and the area-tree tolerance. It leaves out edge cases like validation failures or further required fields, but with 82% schema description coverage and a clear intent statement, the agent has enough to decide when and how to invoke it.

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 82%, so the description doesn't need to re-list parameters. It goes beyond the baseline by clarifying that location is matched loosely against the real area tree, thus allowing town names. It also implies that the same free-form description drives the creation, hinting that many optional fields may get filled from it.

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 ('start'), a specific resource ('a new property listing'), and a source/frame ('in YOUR agency's CRM from a description'). This clearly distinguishes it from sibling tools like create_contact or search_properties, and the 'draft' notice further pins down what it is that is created.

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 'Use when the agent is describing a property they have taken on and wants it in the system' supplies a clear trigger context. The 'never published / on the portal' statement provides a strong boundary. It does not name a specific alternative tool, but the usage context is explicit enough.

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