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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description still adds non-obvious behavior: results are bounded (page_size cap), no inference credits are consumed, no metric refresh occurs, and the legacy representation refuses unsupported targets rather than silently omitting them. The refuse-vs-hide disclosure is exactly the kind of side effect an agent could not deduce from the schema or annotations.

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?

Three sentences, front-loaded with the read scope before the exclusions and pagination rules; no sentence is filler. The opening sentence is information-dense to the point of jargon ("saved schedule instants, exact versions and native review links"), which costs a little readability.

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 values need no prose, and the description covers scope, exclusions, paging procedure, and representation selection for a four-parameter read tool. Remaining gaps are minor: whether status defaults to all states, ordering behavior, and which tool to reach for a single post are left to the schema or inference.

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 100%, so the baseline is 3; the description mostly restates what the schema already says about representation (dev-app and Google Business targets) and page bounds. It does add the cross-parameter rule that status filter and representation must be held constant while paging, but it calls the cursor "next_cursor" while the input parameter is "after_id", introducing a naming mismatch the agent must reconcile against the output 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?

"Read a bounded live page of organization social post states" gives a specific verb (read/list) and a precisely scoped resource, and the enumeration of what is returned (states, schedule instants, versions, review links) makes the payload concrete. It does not name the obvious sibling webanto_get_social_post, so an agent must infer that list-vs-get is the split, which keeps it below 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 negative clause "Does not schedule, approve, publish, refresh metrics or spend inference credits" is an explicit when-not statement that rules out the mutation and metric sibling tools. It also gives operational guidance for pagination ("Follow next_cursor with the same status filter and representation") and a decision rule for the representation parameter. What is missing is a positive routing statement naming which sibling to use for a single post or for publishing.

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