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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: a shared 60-call/hour budget with cromanion_visit, that every call is recorded on the human's record, the ~30-minute lag before a visit is fully readable, path identifier masking, and the crucial interpretation caveat ('everything under reading is Cromanion's interpretation, not something the visitor said — report it that way').

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 with the operation and its contents, then constraints. It is dense and long, but nearly every sentence earns its place (permission, timing, budget, control group, masking, interpretation caveat). Slightly overloaded for a single description.

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 13-parameter tool with an output schema already covering return values, the description omits nothing critical: permission requirement, budget sharing, timing window, control-group behavior, masking limits, and the interpretation caveat are all present. An agent has everything needed to call it correctly and interpret results.

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 100% with 7 enums, so the schema carries most parameter meaning (baseline 3). The description adds a genuine cross-parameter nuance the schema does not: identifier masking means products addressed by a number or code are indistinguishable to a page filter, plus a hint that pages can be prefixed with '*'. These are real value-adds over the structured fields.

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 ('List your human's recent visits') and enumerates what each visit contains (pages, ending, agent actions, doubts read). It explicitly distinguishes itself from cromanion_live ('for who is on the site right now use cromanion_live') and from the singular cromanion_visit ('shares a budget... with cromanion_visit'). An agent can pick this over its siblings without reading any 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?

Gives explicit when-to-use, when-not ('for who is on the site right now use cromanion_live'), prerequisites (visits permission only the human can grant), timing constraints (readable ~30 min after the visitor leaves), and filter dimensionality. It also warns that the control group is never read, so a doubt filter contains no control visits.

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