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

Goes well beyond the annotations: annotations say only destructiveHint=true and idempotentHint=true, while the description discloses that data is broken for every organization member, not just the caller, and sets a minimum permission (admin role). Those are exactly the impact and authorization facts an agent needs before calling.

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?

Two sentences, both load-bearing: the first names the operation, the second front-loads the blast radius and permission requirement. No filler or restated title.

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 single-parameter, no-output-schema, destructive tool, the description covers the essentials: what is unlinked, how broad the damage is, and who is allowed to do it. Nothing an agent needs to invoke it safely 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?

Only one parameter (projectId) and schema coverage is 100%, so the schema already carries its meaning including where to obtain the ID (list_projects). The description adds no syntax or format detail beyond the schema, so the baseline of 3 applies.

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 and resource: 'Unlink a project's Yandex Webmaster host.' This clearly distinguishes it from the connect-side sibling set_yandex_host and from the other disconnect_* tools (ahrefs, bing, ga4, gbp), which target different integrations.

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?

Provides a precondition ('requires at least the admin role') and implies scoping to one project, but never states when to use this versus alternatives (e.g., re-pointing a host via set_yandex_host) or what happens if the host is already unlinked. Usage is inferable from the purpose but not spelled out.

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