analyze_slow_queries

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

Annotations are entirely absent, so the description carries the full burden of behavioral disclosure. The one-liner only states the core filtering operation; it discloses nothing about whether the analysis is read-only, what the default threshold behavior is, how results are ordered or returned, auth requirements, or the max-100 constraint that the schema implies. It does not contradict annotations because none exist, but it leaves runtime behavior largely to inference.

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 a single clean sentence with the core purpose front-loaded and zero filler. It earns the top end of conciseness; the only slight deduction is that for an 11-parameter tool with no annotations and no output schema, the description is on the sparse side of 'appropriately sized.'

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?

Despite having 11 parameters, no annotations, no output schema, and roughly 35 siblings in the same domain, the description provides only the baseline function. It omits how parameter combinations interact, what the return shape looks like, how it differs from get_queries/detect_n_plus_one, and what default behavior occurs when no threshold or limit is supplied. For a tool of this complexity, the description is not complete enough for an agent to call it confidently.

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 100% — every one of the 11 parameters (threshold, requestId, since, uri, limit, count, baseUrl, username, password, token, all) is documented in the schema itself. Per the baseline, the description need not repeat this detail. The word 'threshold' faintly echoes the threshold parameter but adds no syntax or relationship semantics beyond the schema, so a 3 is appropriate.

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 and resource: 'Find slow database queries above threshold.' This clearly conveys what the tool returns and the core filtering criterion. However, it does not contrast with siblings like get_queries or get_query_stats, which also concern queries, so differentiation is left to the agent.

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?

No guidance is given on when to use this tool versus the numerous query-related siblings (get_queries, detect_n_plus_one, get_query_stats, analyze_route_performance). There are no exclusions, no stated prerequisites such as connecting Clockwork first, and no indication of which input strategies (since vs requestId vs count) are appropriate.

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