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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint=false), it discloses payload content the annotations cannot convey: warnings, presentation styles not read, available template catalogs, and a substantive trust boundary note that file text is data not instructions and that file_text counts hidden characters. That is the kind of execution-context detail an agent needs before acting on the returned content.

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 with the imperative 'Start here' and the mutate-relationship, followed by the payload inventory and then the safety caveat. The payload enumeration is a long run-on with parenthetical jargon ('presentation styles moddl does not read, per class'), but nearly every clause carries information an agent would otherwise have to discover by calling.

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 correctly carries the burden of describing return values field by field, and it adds the injection-safety caveat. It omits practical call-shaping details such as output size on large models or what happens when no model is open, which keeps it just short of complete.

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?

The tool takes zero parameters, so the schema baseline is 4; the description adds value indirectly by explaining that storey Names and GlobalIds from this result are the inputs expected by filter.storey and part_of. It gives no syntax for those downstream values, which is the only missing link.

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 ('read the model') and then enumerates exactly what the summary contains: IfcProject GlobalId, schema version, units, TrueNorth, georeference, spatial tree, per-class element counts, warnings, styles_unread and catalogs. That enumeration clearly separates it from get_element, list_properties and check_model, which an agent can distinguish without opening any schema.

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 opening 'Start here: read the model before you change it' gives an explicit calling condition and ordering relative to the mutation siblings, and it names the downstream consumers ('what filter.storey and part_of take'). It stops short of naming alternatives to prefer in specific situations (e.g. get_element for one element, list_properties for a full property dump), so it is clear context rather than full routing guidance.

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