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

With no annotations provided, the description carries the full behavioral burden and does so well: anyone with the link can read but not edit, the link stays current as the note changes, stop: true disables it, secret/Mac-only notes cannot be shared, and agent-initiated sharing is refused. This is unusually complete for a mutation tool with zero annotation coverage.

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 content is dense and front-loaded with the core purpose and options. It is long and somewhat run-on, but nearly every clause adds necessary information given seven undocumented parameters and no annotations. Slightly better paragraphing or bullet structure would improve scanability.

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?

Given no annotations, no output schema, and 0% schema description coverage, the description still covers purpose, usage, parameter meanings, behavioral constraints, refusal conditions, and even the relevant return field tasks_shared. An agent has what it needs to invoke the tool correctly.

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?

Despite 0% schema description coverage, the description explains every parameter: include_tasks, include_transcript, description, invite, stop, id, and workspace. It adds meaningful semantics beyond the bare schema, including that id can be found via search_notes and workspace behaves as for get_note.

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 uses a specific verb and resource: 'Make a public link to one of the user's Caddie notes.' It immediately frames the tool as sharing and lists the app-equivalent options, making the purpose distinguishable from siblings like update_note, pin_note, or search_notes.

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 explicitly states when to use the tool: 'Only when the user asked for the note to be shared or sent.' It also states an important exclusion: when invoked from an agent's own turn inside Caddie it is refused, and the agent should ask the user instead.

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