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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description layers on genuinely non-obvious behavior: retention rules per window, that 30d/90d omit latency, that the 90d % matches the public status page, and the key anti-misinterpretation that an empty window on a paused monitor is not a downtime. This is exactly the context structured fields cannot supply.

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-loads the return shape and then packs retention, paused semantics, and pagination into one dense but well-ordered paragraph with no filler. Slightly telegraphic and compressed, but every clause earns its place.

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 five-parameter, no-output-schema tool, the description fully covers what is returned (per-check fields and window aggregates), the retention constraints on those values, and the pagination loop. An agent has everything needed to call and interpret it correctly.

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 100%, so all five parameters are already documented in the schema. The description adds only a restatement of cursor-based pagination and the window concept, without new semantics for periodo, limite, or apenasFalhas, so baseline 3 is correct.

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 and resource ('checks anteriores de um monitor') plus the exact return shape (horário, ok/falha, latência, erro, resumo da janela), so an agent knows precisely what it gets. It is clearly historical data, implicitly distinct from status_monitor's current state, but it never names a sibling explicitly, which is what a 5 would require.

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 clear context for use: it explains the retention window (8 days for individual checks, summary-only for 30d/90d), the paused-monitor case, and how to paginate with cursor. It does not name alternatives or explicitly state when not to use this tool, so it stops 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.