manage_files

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

With no annotations, the description carries the full behavioral burden and does so well: it states that the tool mutates document-collection state, that save persists to disk, that close|false is destructive and discards unsaved edits, and that switching changes active context for all subsequent operations. The gaps are unmentioned auth/permission requirements and any failure or error semantics.

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 definition is front-loaded with the core purpose and then clearly sectioned into Behavior, Usage, Grammar, Parameters and Returns; each block is useful. The Returns block is redundant since an output schema already exists, which keeps it just short of a 5.

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 single-parameter mutation tool with no annotations, the description supplies the behavior, routing, and per-command syntax an agent needs, and return-value detail is already covered by the output schema. Nothing critical for correct invocation 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 coverage is 0% for the single required parameter, so the description must compensate, and it largely does: it documents the shorthand grammar for each command (new, save|filename|format with default dwg, close|save_changes default false, list, switch|drawing_name) plus the accepted formats. It is weaker on the alternate 'JSON array of file operation objects' form, whose object fields are never specified.

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 a specific set of verbs (open, save, create, close, list, switch) applied to a named resource (CAD drawing files .dwg/.dxf), so the tool's scope is unambiguous despite the generic name 'manage_files'. It also names the siblings it must not be confused with, letting an agent differentiate 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 'When to Use' section enumerates concrete triggers (create blank drawing, save work in progress, close tab, switch active drawing) and the 'Sibling Routing' section explicitly assigns alternatives with the condition that selects them: export_data for plotting/export, manage_xrefs for non-active references, manage_session for connection lifecycle.

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