Search library

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description still adds meaningful non-schema behavior: results are explicitly non-exhaustive, keyword fallback is surfaced in search-mode metadata, and passage_verified/citation_reason must be checked before quoting — real guidance on how to interpret imperfect results.

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 is returned and tightly scoped at five sentences with no filler; each sentence carries a distinct signal (purpose, routing, verification, follow-up, exhaustiveness). Slightly dense with coined jargon ('clip-first', 'revision-bound card', 'uoinks') that costs a first-time reader some parsing effort.

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, the description must carry return-value context and does: it names the key result fields (passage_verified, citation_reason, next_step, card/excerpt URIs) and warns results are not exhaustive. It stops short of describing ordering or what a bare match looks like, but nothing essential to calling the tool correctly 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 two enums fully documented (mode fallback behavior, match forgiving/strict, limit bounds), so the schema carries the parameter burden. The description only hints at the mode parameter indirectly via 'search-mode metadata explains keyword fallback' and adds no syntax or interaction detail beyond that, so baseline 3 applies.

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 (retrieve saved-library matches) and immediately qualifies the shape of the result: bounded, clip-first, with revision-bound card and excerpt URIs. It explicitly distinguishes itself from search_uoinks (whole-item filters) and search_clips (more transcript windows), so an agent can pick the right sibling without opening schemas.

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?

Names the primary use case ('citation-ready research') and two named alternatives with the exact condition that selects each ('whole-item filters' vs 'more transcript windows'). It also gives the follow-up path (read_library_resource, next_step) when a simple search is insufficient.

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