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

With no annotations, the description carries the full burden and does so: read-only semantics, 1000-row cap, 5s statement timeout, zero credit cost, and the validation rules that will reject a query. These are exactly the preconditions an agent needs before invoking, none of which is derivable from the single schema field.

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?

Three tight sentences, front-loaded with the action and immediately followed by the prerequisite and the hard constraints. No restated title, no filler, and every clause carries operational information.

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 tool with no output schema, the description covers validation, limits, cost, and return shape ('returns rows') and delegates column schema to traverse_graph_help. The only omission is any hint about the shape or ordering of returned rows if the agent were to call this without first calling the help 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 100%, so the sql parameter's type and minimum length are already documented; the baseline would be 3. The description goes beyond that by specifying the accepted dialect constraints (SELECT/WITH prefix, no DML/DDL, verbatim caller_user_ids reference), which materially affects how the parameter must be written.

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 (executes SELECT query), the resource (engagement graph), and the return (rows). It also explicitly distinguishes itself from traverse_graph_help, which the agent learns to call first. An agent can tell exactly what this does without opening the schema.

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?

Gives a clear prerequisite routing rule ('CALL traverse_graph_help FIRST') plus hard eligibility constraints (SELECT/WITH only, no DML/DDL, must reference your caller_user_ids). It does not say when the higher-level siblings like get_engagement_trends or get_campaign_stats should be preferred over raw SQL, which is the remaining guidance gap.

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