write_note

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

With no annotations, the description carries the burden. It discloses durability, the 8192-character limit, conditional write semantics, and failure reporting. It doesn't explicitly state that an unconditional write overwrites an existing note, but the conditional guards imply the default behavior; this is a minor gap.

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 tight sentences, front-loaded with the main purpose; conditional logic is explained with inline code formatting. 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?

Moderate complexity tool with 5 parameters and no output schema; description covers main behavior, constraints, and failure reporting. It doesn't specify success return or overwrite semantics, but the core usage and conditional failure mode are sufficiently documented.

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 only 40%, so the description adds essential semantics: value length cap, if_matches as compare-and-set 'when the note still holds that exact value,' and if_absent as create-only. Namespace and key are not elaborated, but their roles are largely inferable from the write/read context.

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 'Write a durable note (<= 8192 characters),' providing a specific verb, object, and constraint. It clearly differentiates from sibling read_note/list_notes by framing this as the write counterpart, and the conditional guards further specify behavior.

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 clearly explains when to use the conditional variants (if_matches/if_absent) and what happens on failure. It does not explicitly name alternative tools, but the contrast between 'write' and the sibling read/list tools makes the intended usage context clear.

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