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

With no annotations provided, the description carries the full behavioral burden and does so well: it explicitly declares 'This is a read: it reports what was found, it does not change anything on the site,' enumerates the fields each insight carries, and warns that rows may be truncated. It omits auth/permission requirements and rate-limit behavior, which keeps it from a 5.

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?

It is front-loaded and dense with useful field semantics, but the pagination explanation is stated twice in nearly identical terms ('pagination.insights carries returned, total_available, truncated and next_offset' vs 'The pagination block reports returned, total_available, truncated and next_offset for every list'), and the long middle field-enumeration sentence is hard to parse. The redundancy costs it points.

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?

There is no output schema, so the description must explain the return shape, and it does: it lists the insight fields, names the pagination object keys, and warns that a 'none of them' conclusion on truncated rows is wrong. Only the site_id parameter and the meaning of 'evidence' are left unexplained, so it is nearly complete for a 7-parameter read tool.

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 71%, and the description adds real meaning on top of it by enumerating the filter dimensions (insight type such as striking_distance/low_ctr/cannibalization, status, action_type, source) and giving an example of insight-type values. It also reiterates offset/next_offset paging and the option to 'raise limit,' though site_id and action_type value space remain undocumented.

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 gives a specific verb and resource: 'Read the findings Murkuz has already stored for a site from its synced Search Console data,' which scopes it well beyond the generic name SEO_Insights. It implicitly distinguishes itself from the Live_* siblings by stressing data that is 'already stored,' but never explicitly names an alternative tool, so it stops short of a 5.

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?

It tells the agent how to interpret results ('Use confidence_label and potential_clicks to decide which findings are worth the customer's time') and lists the available filters, which implies usage. However, it never states when to prefer this over Live_CTR_Opportunities, Live_Cannibalization, or Opportunity_Matrix, and gives no prerequisites beyond the required site_id, so usage guidance is only implied.

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