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

With no annotations, the description carries the full behavioral burden. It does disclose cost ($0.00), latency (<50ms), the backing data source, an accuracy figure, and that misses are free, which is unusually good. However it never says what a pathological outcome looks like – whether a miss returns an empty result or an outage alert, and whether a 'peek' yields a partial/teaser fix that requires unlock_verified_fix to actually apply. That gating behavior is the single most important thing for an agent to know and it is left implicit.

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?

Front-loaded with cost and latency, then the trigger condition, then the value proposition – a sensible order with no filler sentences. Slightly promotional (repeated dollar/token savings figures) but each clause carries signal.

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?

For a 5-parameter, no-output-schema tool that sits at the head of a lookup flow, the description should explain what comes back on hit vs miss and how the result relates to unlock_verified_fix. Return semantics and the relationship to the unlock sibling are the remaining gaps.

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%, so every parameter including the nested packages map is already documented. The description adds no syntax or format guidance for error_text, upstream_domain, or runtime beyond what the schema states, so baseline 3 applies.

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 action (check FixLedger for a Docker-verified fix or active upstream outage alert) triggered by specific error classes, so the resource is clear despite the opaque name 'diagnose_peek'. It does not distinguish itself from the closely related siblings unlock_verified_fix and contribute_verified_fix, so an agent cannot tell from the description alone whether a hit here is actionable or must be unlocked.

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?

Gives an explicit, prioritized trigger list (build/compiler/runtime errors, SDK exceptions, HTTP 4xx/5xx) and a clear ordering rule: call this BEFORE web searches or guessing at edits. That is a strong when-to-use statement. What's missing is sibling routing – nothing says when to escalate to unlock_verified_fix or contribute_verified_fix.

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