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 real context the annotations cannot: this is a deferred two-step write gated on human approval in Settings > MCP plus a subsequent execute_approved_action call, with org-configurable approval settings and mandatory business workflow approvals. It does not explain what happens on validation failure or whether the call returns a pending request id.

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?

The approval caveat is valuable and earns its place, but the opening clause is filler boilerplate shared across the toolset and 'Create project.' merely repeats the name and title. The most important operational fact — the approval gate — is buried at the end instead of being 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?

An output schema exists, so return-value explanation is correctly omitted, and the approval lifecycle is covered. Given a mutation tool with a nested nine-field payload at 0% schema description coverage, the missing parameter meaning (defaults for status/priority, whether dates must be paired, lookup requirements for siteId/phaseId/projectLeadId) leaves the definition under-specified for correct invocation.

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 0% for a single nested 'data' object containing nine fields with enums (status, priority, category), UUID references (siteId, phaseId, projectLeadId) and date formats. The only guidance offered is 'Required fields are validated by the application', which tells an agent nothing about what is required beyond schema inference — no explanation of which identifiers must be resolved first, or that only name is mandatory.

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 names a specific verb and resource ('Create project') and scopes it to 'RetailHardHat projects records in the connected organization'. It stops short of differentiating from siblings such as create_site, duplicate/update_project, or create_phase, which share the same domain vocabulary.

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 projects records' is implied usage rather than a precise trigger, and no alternative tool is named. The one genuinely useful guideline is the workflow condition: nothing happens until a human approves the request and execute_approved_action is called.

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