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

Goes well beyond the annotations: it discloses the downstream effect ('followed stocks lead their home page and followed_stocks'), the eligibility constraint, and the confirmation requirement, none of which appear in readOnlyHint/idempotentHint/destructiveHint. It stops short of saying what happens when the ticker fails the eligibility check (error vs. silent no-op), which is the one behavioral detail a caller would still want.

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 compact clauses, verb-first, with the action stated before the constraints and the confirmation rule placed last where it will be read before invocation. No filler sentences.

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 two-parameter, non-destructive, idempotent toggle with full schema coverage and no output schema, the description covers eligibility, alternative resolution path, side effects, and confirmation. The only remaining gap is failure behavior on an ineligible ticker.

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 100%, with `ticker` examples ('MSFT, 600938.SS') and `following`'s 'false to unfollow' already documented, so the baseline is 3. The description adds only the indirect hint that the ticker must resolve to a stock with influencer opinions and can be found via search — useful but marginal beyond the schema.

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 ('Follow or unfollow a stock') with an explicit toggle, and grounds it in a concrete real-world analogue ('as the Follow button on its page does'). The mention of 'followed_stocks' and 'use search for the ticker' makes it distinguishable from the sibling listing and search tools without opening any 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 an explicit eligibility precondition ('Only stocks with influencer opinions can be followed'), names the alternative action for resolving the ticker ('use search'), and imposes a confirmation policy ('Confirm with the user before calling'). An agent can decide when to call this versus search or followed_stocks from the text alone.

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