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

Goes far beyond the readOnly/OpenWorld/Destructive hints, which already establish a safe read. It discloses non-branded vs branded vs competitor_branded scoring semantics, null-handling for older runs, the meaning of null geo in an engine entry (no data, not zero), what coverage counts, and default competitor trimming with competitors_omitted. That is exactly the context an agent needs to interpret the response.

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 purpose and return shape in one sentence, then spends the rest on field semantics. It is dense and a single paragraph where bullets could improve scanability, but nearly every sentence carries non-obvious information, particularly given the absent output schema.

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 and only two parameters, the description must carry the response semantics, and it does: it enumerates the score families, null conditions for pre-split runs, per-engine null behavior, and coverage counting scope. An agent can interpret a returned object without further docs.

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 100%, so baseline is 3, but the description adds meaning: run_id provenance from list-visibility-runs and a fuller explanation of the detail default, including the 10-highest-plus-tracked-brand cap and competitors_omitted. Slightly redundant with the detail schema description but reinforces the cost tradeoff.

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 ('Get the visibility summary for a specific run') and names the return shape (scores, coverage %, engine breakdown, competitor comparison). It points to list-visibility-runs as the source of run_id, but does not explicitly distinguish this tool from get-visibility-score or compare-visibility-runs.

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?

Clearly tells the agent where run_id comes from (list-visibility-runs) and warns that detail 'full' returns every list and can be very large, giving a concrete case for choosing 'compact' vs 'full'. No explicit when-not or sibling alternative guidance beyond that.

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