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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds real behavior on top: automatic Hebrew prefix normalization (ו, ה, ב, ל, מ, ש, כ), a 300-character snippet cap, relevance ranking, and the exact returned fields with provenance. This is precisely the kind of operational detail annotations cannot express.

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 capability and document count, then return shape, then follow-up routing — a sensible order with little filler. The provenance/verification sentence and the trailing Hebrew title fragment are lower-value and could be trimmed without loss.

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 explicitly enumerates the return payload (title, kind, issuing body, snippet, publication date, source URL, relevance rank), which an agent needs to consume results. Combined with language constraints, normalization behavior, and the escalation path to full text, nothing material is missing for a 3-parameter search tool.

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% (query minLength 3, kind enum, max_results range/default all documented), so the baseline is 3. The description adds language support and prefix normalization for `query`, but says nothing about when or how to use the `kind` filter or how it interacts with the guide-first routing rule.

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 (search) and resource (MISIM.AI public library) plus concrete scope: 2,797 documents and the document categories covered. It also names the follow-up sibling (misim_get_document) for full text, so an agent knows what this tool does and where its boundary lies.

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?

Gives explicit routing guidance ('Guide-first routing' for form 1301 / דוח שנתי / יחיד) and an explicit next-step rule (call misim_get_document with the returned id for full text). It does not explain when to prefer this over the sibling misim_search_legislation, even though the kind enum here includes 'law' and 'tax_treaty' — that overlap is left for the agent to infer.

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