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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description usefully adds partial-update semantics (unsent fields are preserved), which annotations cannot express, but it does not explain why the tool is flagged destructive or what side effects accompany changes such as swapping dest_kind or replacing zip_base64.

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?

A single em-dash-joined sentence with zero padding, front-loading the action and immediately qualifying it with the partial-update rule. Nothing could be removed without losing information.

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?

This is a 24-parameter, destructive mutation tool with no output schema and only 58% schema coverage; the one-sentence description leaves an agent without guidance on interdependent fields (cap_enabled needs cap_period + cap_limit, dest_kind='local' needs zip_base64) or on what the call returns. Given the complexity, considerably more context is warranted.

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?

At 58% schema description coverage across 24 parameters, roughly ten fields (name, tags, notes, group_id, cap_limit, languages, cap_period, aff_network_id, cap_priority) have no description in either place. The description contributes no parameter-level meaning at all beyond the generic 'only the fields you send change' framing, leaving the coverage gap unaddressed.

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 ('Edit') and resource ('an offer'), so it is trivially distinguishable from get_offer, create_offer, and list_offers. It does not explicitly name a sibling it is not to be confused with, which keeps it just short of a 5.

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?

The 'partial update, only the fields you send change' clause implies when this tool is appropriate (incremental edits rather than full replacement), but there is no explicit when-to-use/when-not guidance and no mention of related tools like upload_offer_archive for local-offer ZIPs. Usage is inferable but not directed.

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