Edit part of a hand-written note

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

Annotations already declare destructiveHint=true and idempotentHint=false, so safety is partly covered. The description adds valuable behavior beyond them: the exactly-once precondition on old_text (a concrete failure mode), the heading-level replacement rule ('up to the next heading of the same or higher level; the heading itself stays'), and explicit exclusions. It omits any permission/auth requirements, hence not 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 tight sentences, front-loaded with purpose before the operational rules. Every clause carries information (scope, modes, preconditions, exclusions) with no filler.

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 6-param mutation tool with no output schema and annotations already covering the safety profile, the description covers modes, preconditions, and exclusions. It doesn't state what happens on precondition failure (e.g., ambiguous old_text) or any return shape, but nothing critical for 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 83%, so baseline is 3, and the description clearly exceeds it by explaining mode exclusivity and mode-specific semantics: old_text must occur exactly once, new_text may be empty, section replaces content up to the next same-or-higher heading while keeping the heading, and append adds at the end.

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?

States a specific verb+resource ('Change part of a note') and immediately scopes it to Notes/ or Captures/ and distinguishes it from a full rewrite, which implicitly separates it from brain_write. An agent can tell it does partial edits, not whole-note replacement, without opening the 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?

It gives explicit usage rules: 'Give exactly one of' three mutually exclusive modes, and states what cannot be edited (generated notes, the memory file). It doesn't name a sibling tool directly, but the 'without rewriting it' framing routes the agent away from brain_write.

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