Update property

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write/safety profile is carried structurally. The description does add real value beyond that: partial-update semantics, null-clears-a-field behavior, and field-specific rejection of invalid values. It still says nothing about the confirm/authorization requirement or that changes are not undoable, which for a mutating tool is a notable gap.

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-loads the core action and partial-update rule, then layers the value-format rules in compact parenthetical examples. Dense but every clause carries usable information; the only cost is that the format rules run together without visual grouping, which makes it slightly harder to scan.

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 a nested free-form fields object and no output schema, the description covers input semantics thoroughly enough to call it correctly. It does not mention what is returned or confirm that a read-back/get_property is the way to verify the write, but that omission is minor since no output schema exists.

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 only 33% (just confirm), so the description must compensate, and it largely does: field-name sourcing, date formats (YYYY-MM-DD and DD/MM/YYYY), money formats ('150000', '£150,000', '150k'), area units with sq ft conversion, and the fraction convention for percentages including the '1 or less is already a fraction' rule. Only the confirm parameter's session-approval flow is left to 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 specific verb (change) and resource (fields on a property) and immediately pins down the scope with partial-update semantics: 'Only the fields you pass change; set a field to null to clear it.' That scope statement cleanly separates it from add_property and delete_property without needing to name them.

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 clear operating context and routes the agent to a sibling for field discovery ('Field names from list_property_fields'), which is genuinely helpful. However it never states when to prefer this over add_property/delete_property or any preconditions for the confirm gate beyond what the schema says, so it falls short of explicit when/when-not guidance.

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