Issue Register

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

Despite annotations covering the safety profile, the description adds substantial non-obvious behavior: existing output files are refused, at most 25 snapshots are taken in severity-then-input order within a 210-second budget, failed snapshots degrade to cell notes and warnings, and snapshot capture requires local/SSH transport. It also resolves the readOnlyHint tension by stating 'workbook creation needs no model changes'.

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 description leads with the action and output, then layers constraints, failure modes, and instance-selection rules. It is dense but each sentence carries operational information; only the trailing note about skippedCount could be tightened.

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 6-parameter tool with nested objects and an output schema, the description supplies the capture limits, ordering, failure handling, and instance-selection rules an agent needs. The main omissions are the destination semantics of snapshots and the two undocumented top-level parameters, but the return-value documentation is reasonably delegated to the output schema.

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 only 50%, and the nested 'issues' and 'project' objects have additionalProperties with no schema documentation, but the description enumerates their meaningful fields (title, category, finding, severity; id, requirement_source, recommendation, status, responsible, due, element_ids, snapshot; project name, model, reviewer, client, stage, date, documents) along with allowed values like critical/major/minor/info and snapshot 3d/plan/none. It does not cover output_path or pixel_size, leaving a minor gap.

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 opening sentence states a specific verb and artifact: 'Write a new local .xlsx issue register with element snapshots and review documents.' An agent immediately knows the output is a spreadsheet combining issues, snapshots, and documents. However, it never distinguishes itself from the confusingly similar sibling revit_build_report, so it falls short of the 5 bar.

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?

It gives concrete selection conditions, notably 'If more than one Revit instance is running, document is required; otherwise any instance may respond,' and constrains inputs to '1 to 60 issues'. What is missing is routing guidance against alternatives such as revit_build_report or revit_export, which an agent choosing a reporting tool would benefit from.

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