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

Beyond the annotations, the description discloses the return shape (ranked coordinates, confidence score, an evidence chain of architecture/signage/vegetation/terrain/lighting) and hard privacy limits (no face recognition, no biometric identification, no person matching). The significant omission is cost: depth tiers silently consume 1, 2, or 10 credits, a fact only the schema exposes, and the description never warns that deeper analysis is ten times more expensive.

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 result and its evidence chain are front-loaded in the first sentence, and the ethical constraints come after. The privacy disclaimer is spread over three consecutive sentences ('never the people in it', 'no face recognition...', 'never who is in it') which restate the same boundary and could be compressed into one without losing meaning.

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 no output schema, the description carries the return contract itself and does so adequately: ranked coordinates, confidence, and the evidence chain. For a 4-parameter, nested-object, open-world analysis tool, the only uncovered area is credit cost and sibling routing, both of which are minor against the otherwise complete picture of purpose, limits, and output.

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% and the nested scope object, depth enum costs, and captured_at timestamp semantics are all fully documented in the schema, so the baseline is 3. The description adds only peripheral context ('No EXIF or GPS required' implying image_url/image_b64 sourcing) and does not interpret depth, scope, or the anyOf image-source requirement in its own words.

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 gives a precise verb+resource ('Analyze an image and return its probable real-world location') and even enumerates the evidence classes the result is built from, so an agent knows exactly what it gets back. It never names or contrasts with its siblings verify_location_claim and check_credits, so the agent must infer from names alone which one to reach for.

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?

Strong exclusionary guidance: 'No EXIF or GPS required', 'It answers where an image was taken, never who is in it, and must not be used to locate or track a person' tells the agent clearly when not to invoke. However, it gives no routing to the obvious alternative (verify_location_claim) even though the tool accepts a claimed location via scope, leaving the agent to guess which of the two performs the verification.

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