Save My Tool

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

Going beyond the annotations, the description discloses that compilation happens without execution (a meaningful safety signal for code-accepting tools), that a two-step token handshake gates the save, and that confirm_token is returned. It does not say what the destructive save overwrites or whether an existing tool with the same name can be replaced, which keeps it below a 5.

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?

Three short sentences with the action front-loaded and no filler; the return-value sentence is informative rather than redundant. The only weakness is that the trailing sentence about the token handshake partially repeats the second sentence's clause about the handshake.

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 destructive, non-idempotent, seven-parameter tool with zero schema coverage, this is thin. The output schema excuses not explaining return values, but the description never explains how an agent obtains the first token, what 'mode' changes, or what happens when overwriting an existing tool.

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 0% across seven parameters, so the description must carry the burden and it largely does not. It hints that code is C# and that confirm_token belongs to a two-step handshake, but name, description, parameters, mode, and tested_revit_years receive no explanation of format, constraints, or effect.

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 names concrete operations (compiling C# and a schema without execution, then saving a 'revision'), which conveys more than the bare name. However, 'save a revision' is ambiguous about what is being saved — a tool definition being registered/updated — and it draws no boundary against siblings such as revit_run_tool, revit_get_tool, or revit_delete_tool.

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?

There is no explicit when-to-use guidance and no mention of alternatives. An agent cannot tell from this text why it should call revit_save_tool rather than revit_run_tool or revit_execute_code, nor what prerequisite state (a compiled draft, a prior token) must exist first.

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