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

Goes beyond the annotations by disclosing a real prerequisite (host resource access), that no source is fetched, that geometry is bounded to WGS84, and that the tool performs no legal parcel verification and no file edits. The concrete meaning of 'bounded' (extent/vertex limits) and any failure modes are left unstated.

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?

Single compact sentence with the core action front-loaded and no filler. The trailing clause 'bounded WGS84 geometry, no source fetch, legal parcel verification or file edits' is elliptical enough that the scope of the negation is momentarily ambiguous.

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?

An output schema exists, so return values need not be explained, and the annotations already carry the safety profile. What remains — prerequisites, non-goals, geometry bounds — is mostly covered, though the limits of 'bounded' and how host resource access is granted are not.

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?

With 0% schema description coverage on a nested object (name, resourceUri), the description only partly compensates: 'user-selected .geojson file' hints at the .geojson filename constraint and 'Host resource access required' hints that resourceUri is a host resource reference. It never states what a valid resourceUri looks like or that both sub-fields are required.

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 and resource: opens a user-selected .geojson file read-only in Atlas AI. It is clearly distinct from the analysis/planning siblings, but it never names a sibling or alternative (e.g., open_atlasly_workspace) to reinforce the distinction.

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 only implied: the agent must infer this applies when the user supplies a local .geojson file. There is a useful prerequisite in 'Host resource access required', but no explicit when-not conditions or routing to related tools such as open_atlasly_workspace or analyze_site.

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