doctor

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

With no annotations, the description carries the full burden, and it does the most important part well: fix=True trashes duplicates and empty folders, and that the removal is recoverable from _Trash. It still does not say whether saved search pages or localhost links are ever removed, nor whether dead-link checking has network cost or latency.

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?

Two sentences, no filler, and the high-stakes detail (fix=True is destructive but recoverable) is placed second where it is still highly visible. The telegraphic '(+ dead links if asked)' is compact but slightly ambiguous for a boolean named check_dead_links.

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 return values need not be described, yet the description helpfully enumerates what the report contains and clearly flags the one mutating behavior and its reversal. Remaining gaps are minor: no confirmation/permission requirements and no scope boundary on what fix leaves untouched.

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%, so the description must define both parameters, and it does: fix=True triggers trashing with a stated recovery path, and check_dead_links is covered by '(+ dead links if asked)'. The semantics are conveyed, though 'if asked' is loose phrasing for a boolean flag.

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 name 'doctor' is opaque, but the description immediately specifies the operation and its outputs: a health report covering duplicates, empty folders, saved search pages and localhost links. That is specific enough to separate it from siblings like tree, search and trash, though it never names the domain (bookmarks) or differentiates against any sibling by name.

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 implied rather than stated: run it to audit for cleanup, and pass check_dead_links 'if asked'. The fix=True path is described, but there is no explicit when-to-use/when-not guidance, no prerequisites, and no mention of whether the report is safe to run repeatedly.

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