Shared Coordinates

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description adds substantial behavioral context beyond that: return units (mm, degrees) and precision (one decimal), list caps at 100 without pagination, empty sharedSiteFromLinks behavior, error-on-failure semantics with no partial data, and the multi-instance targeting rule. This is exactly the kind of non-obvious runtime behavior an agent needs.

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?

Five sentences, each earning its place: purpose, return format, list limits, error behavior, and instance targeting. The most decision-relevant information (purpose) is front-loaded, and dense clauses like 'capped at 100 without pagination, with total counts' convey maximum information per word without bloat.

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?

Given the tool's moderate complexity — three optional parameters, a read-only safety profile fully covered by annotations, and an output schema present — the description covers everything an agent needs to invoke it correctly: what it returns with units and precision, failure mode (error, not partial data), non-paginated caps, and the multi-instance routing rule. Timeout semantics are already fully specified in the schema, so nothing material is missing.

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%, so the baseline is 3. The schema's parameter descriptions are exceptionally detailed (document substring matching, timeout budget semantics, pickup timeout lifecycle), and the description body adds no parameter meaning beyond restating the multi-instance rule already present in the document parameter's schema description. The description neither compensates for gaps nor adds new param-level value.

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 'Read project and survey coordinates before an export or hand-over' — a specific verb, resource, and temporal context that immediately tells an agent what the tool does and when it matters. It further enumerates the concrete outputs (base/survey points, active site, project locations, link offsets), making it clearly distinguishable from siblings like revit_document_info and revit_links_status without opening their schemas.

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 phrase 'before an export or hand-over' gives clear situational context for when to invoke this tool, and the document parameter's schema explicitly names revit_list_instances as the alternative when the agent needs all matching instances rather than a targeted document. However, the description does not explicitly state when NOT to use this tool relative to its closest siblings (e.g., revit_links_status for link health), so exclusions are incomplete.

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