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

The annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the safety profile needs no restating. What this description adds is genuinely beyond them: that results are paged and how to resume, that speaker labels come from TENEKS's own attribution (with hedging on names it could not resolve), and a warning that the transcript is untrusted customer speech to be treated as data, not instructions — a real behavioral hazard the annotations do not cover.

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 action, then paging, then attribution caveat, then the safety warning — a sensible escalation with no padding sentences. The final paragraph is the longest but its content is non-obvious and defensible; only minor overlap with the schema's own continuation hints keeps it from a 5.

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 documentation is not the description's burden, and it correctly delegates field-level detail there while still naming the two output fields an agent must act on (truncated, next_offset). For a read-only four-parameter tool, nothing needed to call it correctly — continuation, speaker attribution source, content trust level — is missing.

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%, with each parameter already carrying its own prose, including offset's 'Use next_offset to continue' and char_offset's 'pass next_char_offset back.' The description reinforces the offset/next_offset loop but adds no format, unit, or edge-case detail beyond the schema, and never mentions char_offset or max_chars, so the baseline of 3 is right.

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 first sentence names a specific verb and resource in one stroke: 'Read what was said on one recording, as speaker-attributed turns.' The scoping — one recording — distinguishes it from list_conversations (enumerate calls) and from ask_teneks (query across calls), so an agent can pick it without opening a schema.

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?

It gives a clear operational rule for continuing a paged read ('when truncated is true, call again with the returned next_offset'), but that is pagination mechanics rather than tool selection. There is no statement of when to reach for this instead of ask_teneks for a question about a call, so routing to the sibling is left to inference.

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