zornade_parcel_locate

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does add useful behavioral context: the return value composition ('Returns matching parcels with FID, municipality and centroid') and hard constraints (max 10 points, max 0.05 degrees per bbox side). However, with 0 required parameters it never explains what happens when called with no location arguments or with conflicting modes (lat+lng alongside bbox), and it says nothing about error behavior or pagination beyond the limit param. Partial disclosure with notable gaps.

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?

Three sentences with zero waste: purpose statement, mode/format breakdown, and return-value disclosure. The purpose is front-loaded, exact input formats are inline, and constraints are embedded rather than stated as afterthoughts. Every clause 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 moderately complex tool (5 params, 3 distinct modes, no annotations, no output schema), the description covers the critical decision surface: which mode to use, exact string formats, limits, and what comes back. The only real gaps are edge-case behavior — invocation with no location parameters and conflicting-mode handling — which an agent could reasonably encounter given 0 required params. Otherwise complete enough for correct selection and 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 100%, setting a baseline of 3. The description earns above baseline by revealing that lat/lng, points, and bbox are not independent optional parameters but three mutually exclusive modes — semantics the schema cannot convey by listing them all as optional. The description also confirms the return fields (FID, municipality, centroid) that relate to what the tool yields. This is genuine added meaning beyond per-parameter schema text.

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 opens with a specific verb+resource+method: 'Find cadastral parcels by coordinates or bounding box.' The three-mode breakdown (single point, multiple points, bounding box) makes the tool's scope concrete and clearly differentiates it from siblings like zornade_parcel_by_id (find by ID), zornade_geocode_search (address→coordinates), and zornade_geocode_reverse (coordinates→address). No ambiguity remains about what this tool does.

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 contextual guidance: use this tool when you have coordinates, point lists, or a bounding box, and it precisely explains each mode's input format. However, it never names sibling alternatives or states when NOT to use it (e.g., use zornade_parcel_by_id when you already have a parcel ID). The usage context is clear, but exclusions and alternative routing are left to inference.

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