list_projects

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description does add one real behavioral fact beyond that — only currently open projects are returned, not all projects on disk — but it does not explain ordering, cost, or what an empty result means.

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?

A single front-loaded sentence with no filler. The scope constraint ("Open projects") comes first and the returned fields follow, which is the right order for scanning.

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?

An output schema exists, so the description does not need to explain return values, and with zero parameters there is little else to cover. The only gap is the absence of any pointer to sibling tools for retrieving or opening a specific 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description's field list (path, unsaved-changes flag, sequence/clip counts) describes output, not inputs.

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?

"Open projects with path, unsaved-changes flag and counts of sequences and clips" states a specific verb (list, implied by name) and resource, and scopes it to currently open projects. It is clearly distinguishable from singular siblings like get_project and from list_sequences/list_bin, though it never names those siblings explicitly.

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?

Usage is only implied: the word "Open" tells an agent this covers the currently open project set, and the name makes list-vs-get obvious. There is no explicit statement of when to prefer this over get_project or how it relates to open_project/new_project, leaving routing to inference.

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