team_read_records

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

Annotations already declare readOnlyHint, openWorldHint=false and destructiveHint=false, so safety is covered. The description does add one real behavioral caveat — results are stored bounded snapshots rather than live native data — which affects how much the agent should trust freshness. That caveat is phrased abstractly ('complete-native access is explicitly distinguished from...') and omits pagination behavior, ordering, or result size, so it is useful but thin.

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 main capability is front-loaded in the first sentence, which is good. But the third sentence largely restates the second in more abstract language ('explicitly distinguished from stored bounded snapshots') without adding actionable detail, so the payload is diluted by a near-redundant clause.

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?

With no output schema, 0% parameter documentation, and five inputs including a cursor-like 'after', the description should explain what a page of records looks like and how to page through them. It covers neither, so an agent can identify the tool but not reliably drive its pagination or interpret its node/board identifiers.

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% for five parameters, so the description must carry the burden and it does not: boardId, nodeId, nodeKind (the enum member/workflow choice), and especially 'after' (cursor id? offset?) and 'limit' are never mentioned. Only 'for one node' vaguely gestures at nodeId/nodeKind, leaving the agent to guess the pagination contract.

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 ('Page') plus an enumerated set of resources ('recorded work observations, relayed public-host snapshots and execution receipts') scoped to one node, which lets an agent distinguish this read tool from the record/append siblings. The jargon ('public-host snapshots', 'execution receipts', 'node') is never defined, so the resource identity is clear in shape but fuzzy in substance.

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?

'Does not directly read native threads or private host sessions/databases' gives an explicit when-not boundary covering the most likely misuse. However, it names no alternative tool among the many siblings (team_panel, team_import_thread_page, team_snapshot), so the agent must still infer where to go for native thread access.

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