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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds value beyond them by disclosing the return shape ('ranked pages with snippets and urls'), which matters because there is no output schema. It says nothing about ranking factors, pagination, or match behavior (e.g., fuzzy vs exact).

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 English sentence is tight and front-loads the verb, scope and return shape with no filler. The trailing Russian restatement ('Поиск по сайту') duplicates the information for no functional gain, which is the only waste.

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?

With no output schema, the description usefully covers what comes back, and annotations cover the safety profile, so an agent has enough to invoke it. The main residual gap is the undocumented limit parameter and any guidance on choosing this tool over the list_* siblings.

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 75%, with lang, query and sections documented in the schema while limit carries no description. The description only echoes the section names already present in the enum and adds no syntax, matching or defaulting guidance, so it does little beyond what the schema provides.

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 ('Keyword search across About, Services, Portfolio and Blog') and even scopes the return shape ('ranked pages with snippets and urls'). This clearly separates it from the get_*/list_* siblings, which retrieve known items rather than search by keyword.

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?

Usage is implied by the word 'search' and the section list, so an agent can infer this is the tool for unknown-location lookups while get_*/list_* are for known items. However, no explicit when-to-use, when-not-to-use, or alternative is named, leaving the routing to inference.

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