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

Annotations already indicate readOnly=false with a write side effect, and the description adds the practical consequence: the email, and that there is 'no other way to reach them afterwards.' It also discloses a non-obvious return behavior: it returns immediately bookable tutors, not just a confirmation of the handoff. It does not describe post-handoff timing or team response expectations, but the annotation context sets the bar harm modestly.

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?

Purpose, prerequisite, fallback branch, and return hint — four short sentences in decision order, each doing work, none of it redundant. The most important constraints (ask for email, otherwise use search_tutors) are stated directly and early.

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 tool with five simple paramegab no output schema, it covers what the tool does, what input is non-negotiable, when not to use it, and the shape of the result. What remains unspecified is the exact structure of the returned bookable tutors and any expected lateness in the human-tutor follow-up, but these are minor gaps given the simplicity.

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%, so the baseline is 3. The description elevates the required email parameter from a plain field to a decision rule: it must be sourced from the student, never guessed, because it is the only reply channel. That's the kind of parameter meaning that shapes behavior 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 concrete verb and target ('Hand a tutoring request to the iTutorOnline team so they can line up a human tutor'), going well beyond the tautological name and title. It also clearly differentiates from sibling tools: it hands off a request, while the others fetch profiles, reviews, or create bookings.

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 an explicit precondition and step: 'ask the student for one before calling this.' Also encodes a conditional fallback to a sibling: 'If they will not share an email, use search_tutors instead and give them a profile link.' That is a true when-to / when-not-to rule with an alternative named.

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