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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds real operational context: unscoped calls page the entire catalog, unknown IDs are echoed back (reinforced by the schema), and descriptions=true trades listing size for meaning. It stops short of mentioning response size limits or rate behavior for full-catalog paging, so it is strong but not exhaustive.

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, then the ID workflow, then the downstream rule — a sensible order with no filler. It is dense, packing multiple clauses into semicolon-chained sentences, which is efficient but slightly harder to scan than shorter discrete statements.

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?

An output schema exists, so return structure need not be restated, yet the description still characterizes what each catalog kind contains. With 8 parameters, a required property_id/kind pair, and cross-tool dependencies, everything an agent needs to call this correctly is present.

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 baseline is 3, but the description earns more by explaining the interaction between ids and search (ids first, search as fallback, otherwise full paging) and by clarifying that goal metrics require a goal_id sourced from d8a_get_property_context. It does not add anything about limit/offset or the sources filter beyond the schema.

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 ('check what a dimension, metric or transformation means and how to use it') and enumerates what each kind returns: value type, scopes, filter operators for dimensions; unit and parameters for metrics. This distinguishes it cleanly from the sibling run_* tools, which consume the IDs rather than explain them.

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 an explicit precondition ('before a query'), two retrieval modes ('Pass ids ... or search; without them it pages through the whole catalog'), and names the downstream consumers (d8a_run_query, d8a_run_funnel, d8a_run_paths) with the rule 'never guess'. It also routes to d8a_get_property_context for the IDs and goal_id, which is exactly the alternative-selection guidance an agent needs.

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