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

Far exceeds the destructiveHint/openWorldHint annotations: it discloses replace-vs-preserve semantics, null/[] clearing behavior, add/remove alias semantics, that model edits are plan-checked and do not launch a scan, that archived sites are refused with site_archived, that writes are staged (inspect after partial failure), and that scan snapshots are untouched.

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?

Dense but largely front-loaded, leading with the read-first instruction and the field taxonomy before edge cases. Every clause carries required semantics; it is long but appropriate for a 12-parameter mutation tool, though a few sentences run together.

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?

Given an output schema exists, return values need not be explained, and the description fills all remaining gaps: destructive clearing behavior, error code (site_archived), prerequisite read, partial-failure recovery, and explicit scope exclusions. 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?

With only 17% schema coverage, the description carries the load and does so richly: it maps each field to its effect (brandName vs industry/description/market text, products vs strategy products), specifies replace-vs-merge for lists, and explains add/remove alias groups and null-clearing for strategicGoal and models.

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+resource: 'Edit one brand Site's current profile and strategy note.' It names the exact editable fields and clearly distinguishes itself from siblings like update_topic, update_client, and update_product by scoping to the Site's profile/strategy.

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?

Explicitly instructs 'Read get_site first,' names the alternative for retirement ('use archive_site'), states required preconditions ('At least one effective edit is required'), and lists what is not editable (URL, primary domain, Client reassignment, Topic fields). This is unusually complete routing guidance.

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