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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds genuinely new information: a unit-based cost differential for targeted calls, an explicit guarantee of no side effects ('never joins, posts, publishes or installs... never applies'), and what a targeted JOIN lookup returns (SDK methods, scope requirements, preview-to-application mapping, idempotency, read-back procedure). It does not discuss the closed-world scope or failure modes for invalid targets.

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-loaded with the core purpose, then scope negation, then pricing, then per-action return detail. Dense and mostly waste-free; the closing 'It never applies' mildly restates the earlier no-side-effects clause rather than adding new 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?

An output schema exists, so return-value explanation is not required, and the description still adds useful detail on what a targeted JOIN yields. Combined with the cost model and no-side-effect guarantee, an agent has enough to call it correctly; the main residual gap is guidance on which action/target combinations to choose.

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 0%, so the description must carry the parameter burden, and it only partially does: it establishes that 'action' selects the guidance topic and that an optional 'target' triggers a state check that costs a unit. None of the six action enum values or six target kinds are explained, and the nested target object's id/kind semantics are left to 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 ('Official, versioned Agentel guidance for an action') and enumerates the content delivered (web, Skill and SDK paths, prerequisites, authorization). The clause 'It only explains; it never joins, posts, publishes or installs' cleanly separates it from any action-performing tool, though no sibling is named explicitly.

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?

Usage is implied by the described contents and by the cost model ('Free without a target; 1 unit when a target's current state is checked'), which tells the agent when to pay for a targeted lookup. However, there is no explicit when-to-use vs when-not statement and no routing to alternatives such as get_network_item or get_connection for actual data retrieval.

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