monica_reference

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds genuinely useful behavioral detail beyond them: it scopes destruction to the delete action and states the safety requirement 'Deleting needs confirm: true.' It also notes the optional protocol format for contact field types. It does not describe what deletion affects or the response, but it meaningfully complements the annotations.

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?

It front-loads the identity of the resource, then uses bullet separators to break out the actions compactly. Every clause carries information (the enumerations, the protocol example, the confirm requirement). It is appropriately sized with little waste.

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 an 8-parameter, four-action, destructive tool with no output schema, the description covers the main mechanics but leaves meaningful gaps: 'category' is undocumented, the per-action required/optional field mapping is only gestured at, and with no output schema the shape of list results is unexplained. Adequate but not fully self-sufficient.

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 only 25% (2 of 8 params), so the description must compensate, and it partially does: it explains filter ('optionally filtered by text'), protocol (with the https://instagram.com/ example), confirm: true, and implies name for create/rename plus the kind enumeration. However the 'category' parameter is never mentioned anywhere, and per-action required fields are left as 'see tool description' without being fully spelled out. Net partial compensation.

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 states this is Monica's set of reference lists and enumerates the exact kinds (genders, countries, currencies, activity_types, relationship_types, contact_field_types, tags), and it separates what each action does. The framing that these are lists 'which other tools match names against' implicitly but clearly distinguishes it from the sibling entity-CRUD tools. It is clear, though it never states the purpose in a single crisp verb+resource phrase.

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 clear routing context: 'list' returns the values other tools match against, and create/rename/delete apply specifically to 'your own' activity types, contact field types and tags — implying that genders/countries/currencies are read-only. The filter use for list is described. There is no explicit 'do not use this for X' exclusion, so it stops short of a full when/when-not statement.

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