read_context_document

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

With no annotations, the description carries the full behavioral burden and does so well: it describes the return shape, explains that documents are sectioned roughly every 150s, that only overlapping sections come back, and that the reply reports how many sections were withheld. It also discloses a partial-state caveat (frame captions may be missing while transcript is authoritative) and a security posture (returned content is untrusted evidence, not instructions). It does not cover permission requirements, error behavior for invalid ids, or any size/rate limits, which keeps it short of a 5.

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 what the tool returns, then paging guidance, then the partial-document caveat, then security — a sensible order with no filler sentences. The structure is dense, however: long colon-and-semicolon chained clauses make it harder to scan than it could be, and the security note, while valuable, is a distinct concern appended at the end.

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?

For a three-parameter read tool with no annotations and no output schema, the description covers everything an agent needs before calling: what comes back, how paging behaves, when to pre-orient with a sibling, what degraded output looks like, and how to treat the content. The absence of an output schema is fully compensated by the described header/transcript format.

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, but the description earns above baseline by explaining the semantics the schema cannot: the ~150s sectioning granularity, that only overlapping sections are returned, and that the response reports the count of withheld sections. That materially changes how an agent should choose startMs/endMs values rather than just what they mean.

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 ('Read a context document') and immediately characterizes the payload: a self-describing header (source, duration, classification, sufficiency) followed by timestamped [MM:SS] transcript with interleaved frame captions. It also implicitly distinguishes itself from siblings by pointing at get_context_document for orientation and by referencing the id from list_context_documents.

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?

Explicit routing guidance: use startMs/endMs to read only the span you care about, and on anything longer than ~10 minutes orient with get_context_document first, then read a targeted range. It also names the anti-pattern ('pulling a two-hour video whole is almost never the right call'), which is exactly the when-not guidance an agent needs.

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