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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds genuinely non-obvious behavior: nothing is committed until a human approves the exact request and execute_approved_action is called, and MCP approval requirements are admin-configurable. That is meaningful extra context about the mutation's gating and reversibility that annotations cannot convey. It stops short of saying what happens on rejection or how the pending request is represented.

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?

"Create site." is pure redundancy after the title, and the trailing three approval sentences are boilerplate that could be compressed. The valuable approval-gating fact is present but buried mid-paragraph rather than front-loaded.

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 mutation with a deep nested schema and an output schema, the approval-gating workflow is well covered, but the description says nothing about the payload's substantive fields or which identity/ownership context the site is created under. Given 0% schema description coverage, the description leaves the majority of the input contract unexplained.

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?

There is one top-level parameter containing a large nested object (~25 properties) with 0% schema description coverage, so the schema documents types and enums but not meaning. The description only says "Required fields are validated by the application," giving no field-level guidance on name vs. siteNumber, the status/classification enums, or the financials/demographics sub-objects.

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 says "Create site" and "working with RetailHardHat sites records," which identifies the verb and resource but adds nothing beyond the tool name/title. It does not distinguish create_site from near-neighbors like create_project, create_phase, or create_target_location, so an agent gets no real disambiguation.

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?

"Use this when working with RetailHardHat sites records" is circular rather than a usable trigger condition, and no alternatives or exclusions are given. The approval-workflow sentence is the only practical guidance, and it explains process, not when to pick this tool over siblings.

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