add_watch

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

Since no annotations are present, the description carries the full behavioral burden. It discloses that the watchlist is stored on disk and is local, explicitly stating 'Nothing is saved to your Zameen account.' It also explains the seed_with_current parameter behavior. However, it does not mention potential side effects like name conflicts or file overwriting, a minor gap.

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—three sentences—and the core action is front-loaded in the first sentence. Each subsequent sentence adds relevant context (relationship to check_watch, seed behavior, local nature) without redundancy. It is appropriately terse, though it could be structured more to highlight parameter usage.

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?

With 12 parameters, 0% schema coverage, and no annotations, the description is not complete enough. It explains the general concept and one parameter, but omits definitions for the remaining parameters and how the search criteria are composed. While an output schema is present, the tool's input semantics are underexplained, forcing an agent to guess during invocation.

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%, so the description must compensate but fails to. It only briefly explains 'seed_with_current' and does not define any of the other 11 parameters (purpose, agent_tier, min_area_marla, etc.). Agents are left to guess meanings of parameters like 'purpose' and 'exclude_promoted', making the description inadequate for a 12-parameter tool.

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 starts with a clear action: 'Create a named local watchlist from search criteria (stored on disk).' It specifies the resource (watchlist), the basis (search criteria), and immediately contrasts with account-level operations by noting 'Nothing is saved to your Zameen account — this is a local file.' This effectively distinguishes the tool from siblings like search_properties and account_status.

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 mentions the companion tool check_watch ('Watches are re-checked later with check_watch') which implies a monitoring workflow, but it does not explicitly state when to use add_watch instead of search_properties or when to avoid it. There is no explicit 'use this when' or 'use search_properties for one-time searches' guidance, leaving some decision-making to inference.

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