List top queries

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

Annotations already indicate readOnlyHint, idempotentHint, openWorldHint, and non-destructive nature. The description adds value by specifying the data source ('pg_stat_statements'), ordering (by total execution time), and result size (top 50), which goes beyond what annotations provide.

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?

The description is two sentences, but the first sentence ('List top queries') is redundant with the name. It could be removed without loss. Otherwise concise and clear.

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?

Given the tool has one parameter, is read-only, and has no output schema, the description adequately covers the essential: it lists top 50 queries, sorted by execution time, from a Postgres instance. It references the API endpoint for further context. The annotations complete the safety profile.

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 0%, so description must compensate. It explains that postgresId is the ID of the Postgres instance, adding meaning beyond the raw schema which only defines it as a string. This is sufficient for correct usage.

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 clearly states the tool lists top queries by total execution time on a Postgres instance, specifying the top 50. It distinguishes from sibling tools like 'render_list_postgres' (which lists instances) and 'render_list_postgres_processes'.

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?

The description implies usage for querying top queries on a specific Postgres instance via the required postgresId. However, it does not explicitly state when to use this tool versus alternatives like 'render_retrieve_postgres' or other list tools, leaving the context implicit.

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