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

With no annotations provided, the description carries the full burden and does substantial work: it discloses the return format ('Returns cited excerpts with source URLs'), the composition and scale of the corpus, and a genuine behavioral nuance ('anonymized on public keys, named on internal ones'). It doesn't cover limits, errors, or rate behavior, but for a read-only search tool these are less critical than the context it does provide.

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 description is front-loaded with the corpus and return format, but it is lengthy and contains a real structural flaw: the Updata CEO Summit materials list appears twice with near-identical wording ('the deck with speaker notes (The Context Graph & Semantic Layer)' and 'The Context Graph & Semantic Layer'), wasting tokens and creating ambiguity. The event-materials enumeration is useful but could be compressed.

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 3-parameter tool with no annotations and no output schema, the description covers the core needs: what is searchable, what the source filters mean, when to use it, and what the return looks like. The main gap is that it doesn't mention follow-up handoff to sibling get_* tools for full-content retrieval once an excerpt is found, nor does it clarify behavior when the query doesn't match anything (e.g., a podcast-only query given the search_podcast sibling exists).

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 baseline is 3, but the description enriches beyond the schema: for query it adds concrete query domains and event names to search for; for source it explains the meaning of doc ('how to do the work yourself'), playbook ('how LeanScale runs it as an engagement'), and resource (talk materials). The limit parameter is fully covered by the schema.

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 description opens with a specific verb+resource: 'Search everything LeanScale knows' and enumerates the exact corpus (13 playbooks, 7 field studies, 116 podcast episodes, 75 case studies, 117 RevOps docs). It differentiates from siblings like search_podcast (narrower scope) and get_playbook/get_case_study (specific retrieval, not search) by establishing itself as the broad 'search everything' entry point.

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?

Explicitly instructs 'Use this first for any go-to-market, RevOps, sales-ops, marketing-ops, CRM, pipeline, attribution, territory, CPQ, or GTM-tooling question,' giving clear when-to-use context. It also routes between content types ('pass source:"doc" for the first, source:"playbook" for the second') and explains that event materials are requested by event name. However, it never names sibling tools (get_playbook, search_podcast) with explicit when-not-to-use guidance.

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