librarian_tell

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

With no annotations, the description does real work: it discloses that submissions are never rejected as irrelevant and are persisted for future sessions, which tells the agent this is a low-risk, always-succeeding write. It omits deduplication/overwrite behavior against existing knowledge and any size or auth constraints, keeping it below 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?

The leading imperative and the content inventory are front-loaded and the parenthetical '(never rejected as irrelevant)' is a tight clarifier. Mild redundancy between 'GIVE the librarian knowledge it doesn't have' and 'something ... it didn't know' costs it a point, but nothing is wasted overall.

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 not be explained, and the acceptance/persistence semantics are covered. However, for a write tool with zero annotations and zero schema description coverage, the undefined `subject` parameter and the absence of any guidance on how entries interact with existing librarian knowledge leave a real gap.

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 0%, so the description must compensate. It handles `caller` explicitly ('optional caller label; leave it empty') and effectively defines `info` through the enumeration of acceptable content, but `subject` — the second required parameter — is never explained, leaving the agent to guess whether it is a heading, a key, or a retrieval tag.

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 ('GIVE the librarian knowledge') and immediately enumerates the kinds of payload it accepts (built things, discoveries, decisions, paths/tools, general context). That framing cleanly separates it from siblings like librarian_ask and librarian_locate, which retrieve rather than contribute.

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?

'Use whenever you know something the librarian got wrong or lacked' gives an explicit triggering condition, backed by the earlier inventory of acceptable content. It stops short of naming an alternative (e.g., librarian_session_log for routine logging) or saying when not to use it, so a 4 rather than 5.

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