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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description is free to add genuinely new behavior: the unavailable/no_demand_snapshot condition and its likely causes, the coverage flags, and the explicit warning that the change in signal count is correlational, 'not a cause'. That is behavior beyond anything the annotations state.

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-loaded with the purpose, and nearly every sentence carries routing or error-handling value. It is dense and slightly run-on, but there is little genuine filler to cut.

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 must describe returns, and it does: the window token, signal counts by type, detector states, coverage, and the previous-snapshot delta. Combined with the error and sibling routing, an agent has everything needed to call and interpret it.

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 description coverage is 100% and there is a single required project_id whose meaning the schema already documents. The description adds no format or syntax 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 ('read the latest search-demand snapshot') and enumerates the concrete signal types it contains (striking-distance queries, competing pages, low CTR, rising/falling queries). It explicitly distinguishes itself from the three adjacent read_* siblings it could be confused with.

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?

Names the alternatives and the condition that selects them: pass the returned window to read_query_evidence for query rows, use read_actions for prioritized work, and read_search_intelligence for keyword volumes from research. It also explains the no_demand_snapshot failure and routes the agent to read_integration_status.

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