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

With no annotations provided, the description fully carries the transparency burden. It discloses fire-and-forget semantics, the discard rule ('a 'worked' report on a server we saw dead is discarded'), the accumulate-only behavior ('Does NOT change the current rating yet'), and the binding via call_hash. This is rich behavioral context beyond what any schema or annotation might provide.

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 moderately sized but dense and purposeful. It front-loads the core purpose, adds key behavioral caveats, and ends with a clear args list. Every sentence earns its place, though the phrasing is somewhat jargon-heavy ('outside-in probing', 'load-bearing') which slightly reduces clarity.

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 six-parameter tool with no output schema and no annotations, the description provides strong context: what, when, why, and key behavioral rules. It explains the data flow to the observatory and the anchoring against probes. Minor gaps include no explicit mention of what the tool returns, but the word 'fire-and-forget' implies no meaningful return value.

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 only 17%, so the description must compensate. It does by explaining 'ok' as success/failure, latency_ms as latency, cost_tokens as cost, and call_hash as 'a hash binding the report to a real call.' While not every parameter gets a dedicated line, the narrative plus the args list provide sufficient semantic grounding.

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 clearly states the tool's purpose: 'AFTER your agent calls a tool, fire-and-forget how it went — success/failure, latency, cost.' It identifies a specific verb (report), resource (how a tool call went), and distinguishes itself from siblings like check_server and should_i_use by being a post-call observability feedback mechanism.

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 description explicitly says to use it after an agent calls a tool ('AFTER your agent calls a tool') and clarifies it is fire-and-forget. It also states an important exclusion: 'Does NOT change the current rating yet (probing stays load-bearing).' While it doesn't name sibling alternatives, the timing and exclusion make usage clear.

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