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

Annotations only cover the mutation/safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds genuinely non-derivable behavior: the data-privacy constraint on what may be transmitted and the two modes of initiation. It does not disclose submission consequences (who sees it, whether it is queued or irreversible), which keeps it from 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 sentences, front-loaded with purpose, then usage triggers, then the critical privacy rule. Nothing is redundant with the title or schema and every sentence carries a distinct instruction.

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 no explanation, and the description covers purpose, both invocation paths, and the privacy constraint that an agent must honor before calling. Nothing required for a correct call 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 description coverage is 100% and the enums for category and initiated_by are fully self-documenting, so the baseline is 3. The description reinforces the message parameter's constraint by restating 'no note content' in the privacy sentence, but adds no syntax or format detail beyond the schema.

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 and resource (send feedback to the Engram team) and enumerates the accepted content types (bug, idea, confusing, works well, missing capability). This clearly distinguishes it from every sibling, which are all note/folder/attachment vault operations.

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?

Gives explicit trigger conditions for both actors: when the user asks to send feedback, and when the model should self-initiate (a tool failed, gave a poor result, or could not do what was needed). It also states an exclusion — never include note content, titles, paths, or personal data — which is the only real usage mistake an agent could make here.

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