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

Annotations declare only readOnlyHint, so the description carries most of the burden and does so well: it states ordering ('newest first'), depth ('its ten latest changes'), and the diff/return format ('- removed, + added' or before/after field values). It omits any failure or empty-state behavior, which keeps it short of a 5.

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 no-argument case and then walks outward to progressively narrower modes; every clause maps to a parameter or a return shape. The telegraphic, comma-chained sentences make it dense to parse but nothing is padding.

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?

With no output schema, the description compensates by describing what comes back (watch attributes, topic finding date/text/sources, line diffs, before/after values). Seven parameters and zero required ones are all accounted for with their valid combinations, leaving only edge cases like empty histories unexplained.

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 the baseline is 3, but the description adds relational meaning the schema cannot: monitor_key alone selects one watch plus its ten latest changes, changes:true switches the whole result set, and change_id drills into a single change. These mode interactions are the real value added.

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?

Specific verb+resource ('Read this person's web watches and what they found') with the three distinct modes (list watches, one watch's changes, history, single change) spelled out. An agent can separate this from manage_web_watch, check_page_changes and watch_web without opening the schema.

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 a concrete when-to-use cue ('use it for "what changed on competitor sites this week"') and maps each argument combination to a distinct read mode, so the agent knows which invocation shape to pick. It never names a competing sibling (manage_web_watch, check_page_changes) as an alternative, though, so there are no explicit exclusions.

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