edit_staff

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

With no annotations provided, the description carries the full burden and excels: it discloses partial-update semantics ('Only provided fields change... STAFF/ADMIN access level — is left untouched'), the PS_ENABLE_WRITES permission requirement, and the guardian rejection behavior. This is rich behavioral context for a mutation tool that annotations would normally be expected to cover.

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?

Well-ordered and front-loaded: the core purpose leads, then the critical permission prerequisite, then the partial-update behavior, then alternative routing, ending with the compact arg list. Every sentence contributes; the permission and exclusion notes are the highest-value info and appear 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 mutation tool with 8 params and 0% schema coverage, this is complete: it covers the permission gate, k part updates, parameter sourcing, sibling alternatives, and an error case (guardians). An output schema exists to carry return-value details, so the description doesn't need to explain them. Nothing an agent needs to call it correctly is missing.

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 0%, so the description must compensate, and it does by listing all 8 args with inline semantics. It adds real value for title (with an example) and staff_id ('The school's own staff/external ID'), clarifying the distinction from user_id. However, several parameter descriptions are terse restatements ('New first name', 'School ID') that don't add meaning beyond the schema, keeping it a notch below perfect.

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 uses a specific verb and resource ('Update a staff member's name, email, phone, title, or staff ID'), enumerating the exact fields affected. It differentiates from siblings by explicitly naming edit_parent as the tool for guardians, and add_class_staff/remove_class_staff for class assignment changes.

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?

Excellent routing guidance: names PS_ENABLE_WRITES as a prerequisite, tells the agent to get user_id from list_staff(school_id), explicitly says class-assignment changes should go through add_class_staff/remove_class_staff, and states that guardians are rejected and to use edit_parent for those. Nothing is left to inference.

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