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

With no annotations, the description carries the full burden and does disclose real behavior: the server persists a snapshot and reports a unified diff on text change. It does not cover what happens on the first check (no baseline exists yet), whether the interval can be changed after creation, reliability/error behavior, or auth requirements.

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?

Three sentences, each doing distinct work: what it does, when to use it, and how to specify the selector. Nothing is repeated from the schema verbatim and the contrast with fetch is front-loaded rather than buried.

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 three-param tool with no output schema and no annotations, this covers the essentials including the return shape (unified diff). The gap is lifecycle detail — first-run baseline behavior and the handoff to watch_diff/watch_history for retrieving results.

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 baseline is 3, but the description earns credit by enumerating the accepted selector grammars (css:#id, css:.class, css:tag, regex:PATTERN, json:$.path, empty for whole body) — a form the schema only sketches with two examples.

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 ('Start watching a URL for changes') and immediately explains the mechanism (snapshot, periodic re-fetch, unified diff). It also contrasts against a plain fetch, which separates it from http_head and the rest of the sibling set.

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?

Explicitly gives the selecting condition: 'Use this when you need to know if something changed since last time - an ordinary fetch cannot tell you that.' That is a clear when-to-use rule, though it never names the adjacent watch_* siblings (watch_check, watch_diff, watch_history) that an agent must pick between.

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