watch_diff

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

No annotations are provided, so the description carries the burden. The verb 'show' and the enumeration of reported categories imply a read-only diff operation, and it usefully defines what counts as a spike. However, it says nothing about prerequisites (needing two snapshots to exist), what happens with fewer than two snapshots, or whether the output is a diff-only summary — gaps that matter for a no-annotation tool.

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 core purpose is front-loaded in the first sentence, followed by a compact enumeration of report contents and a single parameter note. The docstring-style Args block is slightly verbose but every line adds information; nothing is redundant.

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?

An output schema exists, so return-value detail is correctly omitted, and the description explains the parameter that matters. But it omits the precondition that two estate snapshots must exist, and leaves the ctx parameter entirely unexplained, so an agent lacks the full picture needed to invoke it safely.

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 0%, so the description must compensate for both parameters. It documents epss_threshold well (range 0.0-1.0, default 0.10, and the meaning of 'rise' as a spike), but ctx is not mentioned at all in the description or schema, leaving a required-to-pass parameter with zero semantics.

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 with scope: 'Show what changed between the two most recent estate snapshots.' It enumerates the categories of change (KEV additions, EPSS spikes, new CVEs, resolved findings, membership changes), so the agent knows exactly what it returns. It does not name a sibling to differentiate from, e.g. watch_brief or estate_scan, which keeps it below 5.

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?

There is no explicit when-to-use guidance, no prerequisites (it implicitly requires two prior estate snapshots), and no alternatives named. The agent must infer from the phrase 'most recent estate snapshots' that watch_brief and estate_scan are the related tools. This is essentially usage-by-implication only.

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