fastmean_edit_properties

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

Annotations already declare readOnly=false, destructive=false, idempotent=false, so the safety profile is partly covered; the description still adds genuinely non-obvious behavior: nested patches are merges that retain omitted fields, definitions are stored as TEXT, and no source files are written or executed. The merge semantics in particular are information the agent could not recover from the schema. It falls short of 5 because persistence is unclear — whether edits are staged in memory or committed to the project file is never stated.

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?

Roughly four dense sentences, front-loaded with the purpose followed by the per-parameter mechanics and a closing boundary statement. Every line carries information and the example appears before its explanation. Minor deduction for the hard line breaks mid-sentence that make the example payload look like a separate clause.

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?

Output schema exists, so return values need no explanation, and the annotations cover the mutation/safety profile. Combined with the merge semantics, the analysis field domains and the explicit 'nothing is run here' boundary, an agent has enough to call this correctly. The remaining gap is the undefined required `path` and the unstated persistence model behind 'in a new project'.

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 coverage is 0%, so the description carries the full burden. It does well for three optional parameters, giving concrete shape for `updates`, the accepted domains for `analysis` (TD/FD/AOD/SOD/DCOP), and the TEXT storage type for `definitions`. However, the single required parameter `path` is never explained at all — an agent cannot tell whether it is a project file, a directory, or a design name — which is a serious omission the rest of the text does not compensate for.

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 first sentence names a specific verb and concrete resource set: native component parameters, tables, and saved settings. The example payload `updates={"TR1":{"n":2},"SW1":{"Ron":0.01}}` makes the operation unmistakable. It loses a point because the phrase 'in a new project' is ambiguous and it never contrasts itself with the near-identical siblings fastmean_edit_parameters and fastmean_edit_values.

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 one real routing rule — 'File/model interfaces use create_project, not arbitrary parameter paths' — and states that nothing is run or overwritten here. But given three overlapping edit tools (edit_parameters, edit_values, edit_properties), the absence of any explicit when-to-use-this-vs-those guidance forces the agent to infer selection from the parameter names alone.

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