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

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=true, so the safety profile is covered. The description adds useful behavior (writes are actively refused rather than silently ignored, and `get` returns trigger rules, account data, behavior, knowledge items, actions and tracked properties), but it then describes mutation actions and their required params as if they were usable here, which actively misleads about what the tool will do.

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 read-only disclaimer and action list are well front-loaded, but roughly half the text describes update/create/delete operations the tool refuses — content that belongs to the sibling agent_manage and serves only to confuse. The valuable part of the definition could fit in two 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?

The schema is extremely rich (every param is documented with action tags), so the description carries little burden, and the first paragraph supplies the routing and read-action coverage an agent needs. The duplication of agent_manage's write surface is not a gap so much as noise, but it does leave the overall definition ambiguous about this tool's actual capability set.

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 baseline is 3 regardless of the description. The description does add a little meaning (what `get` returns, create_contact_property needing exactly one of field_name/contact_property_id), but most of its parameter detail maps to actions this tool does not expose, and it conflates 'list_items / create_item (params: item_type [required])' when the schema marks item_type as create_item-only.

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 opening line is precise — 'Read agent — this tool changes nothing' — and names the four supported read actions, which clearly separates it from agent_manage. However, the second paragraph opens with 'Manage the AI agent configuration' and enumerates update/create/delete operations, so an agent skimming the definition could conclude this tool can write.

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 routing rule is explicit and front-loaded: anything that writes is on `agent_manage` and is refused here, with the exact list of write actions named. There is no guidance on which read action to pick for a given goal, but the when-to-use-this-vs-alternative condition is stated clearly.

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