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

Annotations give the safety profile (readOnly=false, destructive=false, idempotent=false), and the description goes well beyond them: a postsPerWeek change re-plans the calendar immediately, topping up or trimming unwritten entries and being subject to cadence limits, and autoRenew controls automatic refilling. These side effects are exactly the behavioral context an agent needs before mutating plan state.

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?

The core sentence is front-loaded with the verb and resource, and the closing 'Send only the fields to change' is a useful, tight instruction. The middle is a dense run of parenthetical clauses, but nearly every clause carries distinct semantic value, so little is wasted.

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 6-parameter mutation tool with no output schema, the description covers all mutable fields, their effect, and partial-update behavior; the required 'site' param is documented in the schema. It stops short of stating what is returned after a successful change or how cadence-limit violations surface, which would close the last gap.

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 only 17% (just 'site'), so the description carries the burden and does so well: it explains the meaning of manualKeywordRatio (share of articles from the customer's own keywords vs discovered topics), priorities (restrict to research topic labels; omit to allow all), and the effect of autoRenew, beyond the bare ranges/enum in 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?

The description names a specific verb+resource ('Change plan settings') and enumerates exactly which settings are mutable, so an agent immediately knows the scope. It does not explicitly distinguish itself from near-siblings like update_plan_entry or update_settings, leaving that separation to inference.

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?

'Send only the fields to change' establishes partial-update (PATCH) semantics, which is genuine usage guidance. However there is no when-to-use/when-not guidance and no pointer to alternatives such as update_plan_entry for individual calendar items or get_plan for reading current values.

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