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

Annotations already declare it is a non-destructive, idempotent mutation (readOnlyHint=false, idempotentHint=true). The description adds useful behavior beyond that: it returns the company's latest change and, on an unclear name, returns say_now prompting for a website. It could have said more about permissions or error cases, but the annotation coverage lowers the burden.

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 tight sentences, front-loaded with the core action and example. Each sentence adds distinct information: what it does, how it differs from add_target, and what happens on ambiguity.

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 and only two parameters, the description covers the action, the sibling exclusion, the return value ('latest change'), and the ambiguity fallback. Minor gap: the say_now tool is not listed among siblings, so the fallback reference is slightly under-contextualized.

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 schema documents both parameters. The description adds value by explaining when the optional website parameter is used ('when a reply asked for it') and by connecting an unclear company name to a say_now response requesting the website.

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 ('Starts watching one company'), gives a concrete example ('watch Abiomed'), and explicitly distinguishes this from add_target: 'adding a target does not watch it.' The sibling tool names confirm this differentiation matters.

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 states 'This is the only way a company watch is made; adding a target does not watch it,' routing the agent away from add_target. It also tells the agent the fallback path when the name is unclear: returns say_now asking for the website.

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