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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains what the tool produces, the URL pattern, that the list opens with buildings added, and that actions like compare, AI Read, and tour requests are available there. It could mention side effects or failure behavior, but the core behavior is well disclosed for a link-creation 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?

The description is two sentences with the primary behavior front-loaded. The feature list after the dash is brief and helps the agent understand the output's purpose without adding bloat. Every sentence earns its place.

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 low-complexity tool with three parameters and no output schema, the description is nearly sufficient: it names the output artifact, the input source, and the result behavior. It could be slightly more explicit about what the tool returns and the role of the optional city and agent parameters, but these are not critical blockers.

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 only 33%, so the description needs to compensate, and it meaningfully does for the most important parameter: apartment_names must use the EXACT names returned by search_apartments. It also implies these are finalist apartments. City and agent receive less clarification, but city is an enum and agent has a schema description.

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?

The description states a specific verb and resource: it turns finalist apartments into a Taco Street link that opens the renter's saved list. This clearly distinguishes the tool from siblings like search_apartments, which finds apartments rather than creates a shareable link.

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 description gives clear context: use this tool when finalist apartments have been identified and a shareable shortlist is needed. It also provides an explicit input rule, 'Use the EXACT names returned by search_apartments,' which helps the agent avoid common errors. It does not explicitly list when not to use alternatives, but the intended scenario is clear enough.

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