debug_service

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description usefully discloses that this is a multi-signal aggregate and that metrics are compared baseline-vs-recent and logs are grouped by signature, but it says nothing about cost/latency of a fan-out call, result volume, or the default window (only the schema reveals now-2h).

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 with the verb first and each clause mapping to a distinct returned section; there is no filler. It is dense and list-like rather than scannable, which keeps it just below a 5.

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 carries the burden of describing returns and does so thoroughly for all six signals. Gaps are minor: the default 2h window, expected result volume, and any guidance on cost of a multi-signal fan-out are absent, but nothing essential to invoking it correctly is missing.

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 already 83%, so the baseline is 3; the description adds mapping value by tying 'recent deployments/config changes' to deployments_from, 'failure logs ... grouped by signature' to log_filter/log_limit, and 'problems in the window' to the from_time/to_time pair. That conceptual framing goes beyond the field-level schema text, though it offers no syntax or default guidance of its own.

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?

Opens with a specific verb+resource ('Debug a service') and immediately enumerates the exact signals returned: failure rate, volume, response time baseline vs recent, grouped failure logs, deployments/config changes, problems, and callers/callees. This composite scope is clearly distinguishable from single-signal siblings like search_logs, list_problems, or query_metrics.

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 enumeration of signals implies 'use this for a broad service-level health check', but the description never states when to prefer it over siblings such as investigate_problem (which sounds like an overlapping entry point) or when to drop down to search_logs/query_metrics directly. Usage is inferable but not explicit, and no exclusions or prerequisites are given.

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