query_history_profile

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

The description goes beyond the annotations by disclosing that the tool 'runs it once more' (a re-execution with real cost) and enumerates what the profile returns: operator tree, actual rows, time, memory, spilling, segments skipped. Annotations only state readOnlyHint/openWorldHint, so this re-execution detail is genuinely additive; it still omits timeout behavior and failure modes.

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?

A single front-loaded sentence that packs the verb, input constraint, re-execution caveat and return contents with no filler. It is dense but every clause earns its place; readability slightly suffers from the parenthetical load.

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 correctly enumerates the return contents (operator tree, rows, time, memory, spilling, segments skipped) and clarifies the input is a SELECT/WITH from history. The main gap is the completely undocumented 'key' and 'timeout_s' parameters.

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% and the description never mentions the 'key' or 'timeout_s' parameters. 'from the history' faintly implies key refers to a history entry, but neither the required key nor the timeout default is explained, leaving the parameter burden unmet.

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 (PROFILE) and resource (one read-only query from the history) and pins down the exact artifact returned via '(SHOW PROFILE JSON)' with a field list. This clearly separates it from sibling tuning/plan tools like query_history_plan_tuning or query_history_tuning.

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?

'one read-only query (SELECT / WITH) from the history' tells the agent the applicable scope and that it operates on an existing historical query. It does not explicitly name an alternative tool or a when-not condition, so it lands short of a 5.

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