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

Annotations already cover readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the description is not carrying the safety burden alone. It adds real context beyond them: notes are private to the business, no one is notified, no confirmation prompt is raised, the call returns the new note's ID, and deletion is the reversal path. The only gap is who can see the note surface long-term, which is largely covered by the privacy statement.

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?

Front-loaded and reasonably short, but it repeats the same privacy rationale twice ('Notes are private to your business' and 'client profiles are private to your business'). The phrase 'Adds a blank note' also clashes mildly with the required text parameter, creating avoidable ambiguity about whether content is actually submitted.

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 two-parameter write tool with no output schema, the description covers the essentials: effect, privacy scope, returned ID, reversibility, and the API-key requirement. Nothing critical is missing, though a stronger statement that the note text is the payload would close the gap left by 'blank note'.

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% (text and client_id both documented, with client_id pointing to find_client), so the baseline is 3. The description adds only a mild hint that a note can carry a 'formula' as well as free text, which is marginal value over 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 ('Save a note or formula to a client profile') and names the exact surface where the result appears ('Notes and Forms'). An agent knows precisely what this does 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?

Usage is only implied by the verb 'save a note'. There is no explicit when-to-use versus siblings like glossgenius_get_client or glossgenius_find_client, and no stated preconditions beyond the API-key note at the end. The mention that deletion in the client profile undoes it is the only actionable guidance.

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