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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds non-obvious behavior beyond them – that delete leaves creators tracked but collection-less, that delete requires a two-turn preview/confirm flow, and that update is a sparse patch. It also discloses the tool is 'Free', which is cost context annotations cannot carry. Missing: who can call it and what a create returns.

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 action set, then layers domain semantics, then per-action details – a sensible ordering. It is dense and semicolon-chained, so a couple of clauses (the 'Free' aside) read as tacked on rather than integrated, but no sentence 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?

For a 12-parameter, no-output-schema mutation tool, the description covers the high-risk parts: destructive delete flow, sparse update, and the matching semantics that determine what the collection actually measures. Gaps are minor – no mention of the auth/uid fallback or what the confirmation preview contains (schema covers the token mechanics).

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?

With only 50% schema description coverage, the description usefully compensates: it explains the operational meaning of match_terms (caption must contain a term), the starts_at..ends_at window as the counting scope, and that target_cpm/budget/posts_per_week drive payout and posting-target views rather than being mere fields. Primary keys (collection_id, name) are left entirely to the schema's own descriptions.

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?

Opens with a specific verb set and resource ('Create, update or delete a Creator Tracking collection'), then defines the domain concept (a campaign, posts matched by caption term within a date window). This distinguishes it well from list/get siblings, but it never names an alternative such as track_creators or untrack_creator, so an agent must infer the boundary itself.

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 per-action guidance: 'update changes any field you pass' establishes partial-update semantics, and delete is explicitly gated behind 'the preview + confirmation_token step'. No sibling tool is named as an alternative, so cross-tool routing is left implicit.

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