measure_distance_between_points

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the return shape (summary, confidence, measurements, warnings), an accuracy caveat (depth file without intrinsics capped at low with wide +/-), a failure mode (glass/mirror/black surfaces yield NO_DEPTH_AT_POINT), and a precision floor (points under 3 cm are within noise). Only auth/rate-limit style context is absent, which is largely irrelevant for a read-only measurement.

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?

Front-loaded purpose statement followed by compact parameter notes and then return/edge-case behavior. Dense but every clause carries distinct, useful information; no filler sentences.

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 six-parameter tool with no annotations and 0% schema coverage, the description covers inputs, coordinate semantics, formats, failure modes, accuracy caveats, and return hints. An output schema exists so return values need not be elaborated, yet the brief mention is a bonus rather than a gap.

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 and it does: it documents all six parameters, including accepted path formats (LiDAR/Portrait HEIC, bundle, TIFF, 16-bit PNG mm, NPZ), that point_a/point_b are [x, y] in photo pixels, that rgb_path supplies EXIF focal length, and that units accepts metric|imperial|both.

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+resource ('Straight-line distance between two pixels of a depth capture') and even grounds it with examples ('a doorway width, a shelf gap'). The scope is unambiguous, but no sibling tool is named to differentiate it from measure_object or room_check_doorway.

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?

Usage is implied through the input context ('depth-map pixels when there is no photo', 'with a plain photo the two points must lie on the reference's surface') and it routes the reference parameter to measure_list_reference_objects. However, it never explicitly states when to choose this tool over alternatives like measure_object, so guidance remains inferential rather than directive.

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