execute_readonly_query

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

With no annotations supplied, the description carries the full burden and does disclose the two most important behaviors: queries are strictly read-only (SELECT/WITH only) and results are capped via automatic ROWNUM injection, an enforcement detail an agent could not otherwise know. Remaining gaps are secondary — it says nothing about error behavior for invalid SQL, query timeouts, or the SQL dialect (only inferable from 'ROWNUM').

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 core constraint is front-loaded in a single sentence, followed by a compact Args block, so there is no wasted framing. The only redundancy is the SELECT/WITH restriction being stated twice, once in the summary and again in the sql_query description.

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 values needn't be documented, and both parameters are given meaning plus a row cap. What is still missing for a query-execution tool is error/edge-case behavior and an explicit dialect note, but nothing essential to invoking it correctly is absent.

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 0%, so the description must compensate, and it does: sql_query is constrained to SELECT/WITH queries, and max_rows is given a 1-500 range that is absent from the schema (which only carries the default of 50). Neither is explained with format examples or behavior when the range is exceeded, so it falls short of a 5.

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 states a specific verb ('Executes') and resource ('strictly READ-ONLY query (SELECT/WITH)'), plus the scope constraint of automatic ROWNUM capping. It is immediately distinguishable from sibling tools like list_tables or describe_table, which inspect metadata rather than run queries.

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?

Usage is only implied: the tool is clearly the way to run arbitrary SELECT/WITH SQL, and the read-only limitation implicitly routes writes elsewhere. However, it never names an alternative or states when to prefer it over schema-inspection siblings, and it doesn't say what happens if a caller submits a DML statement.

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