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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, fully covering the safety profile for a search/read operation. The description adds the retrieval-mode behavior (hybrid/semantic/lexical across metadata and artifact content) which is useful. No mention of result ordering, pagination behavior, or status filtering, but with strong annotations the burden is lower. Description aligns with annotations; no contradiction.

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?

Two sentences, both substantive. The first defines scope, the second gives a concrete usage tip. No filler or redundancy. Front-loaded with the core purpose. Could arguably mention pagination or result format but remains efficient.

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 search tool with no output schema and 5 parameters at 0% schema coverage, the description provides the core purpose and one usage pattern but doesn't explain cursor-based pagination, status semantics, or result ordering/format. A read-only search tool with idempotent hints is relatively low-risk, so the gaps are moderate rather than severe. Adequate but with room to explain parameter behavior.

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 0%, so the description carries the full burden for parameter meaning. The description explains mode behavior somewhat ('hybrid, semantic, or lexical retrieval') and implies query usage via the empty-query note, but doesn't explain what 'active/archived/trashed' status means, how limit behaves, or what cursor pagination returns. The enum values for mode are inherently self-explanatory, partially compensating. Marginal value added beyond the schema; 3 is baseline despite low coverage.

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?

Description states a specific verb ('find') and resource ('current shared context') with clear scope: retrieval across metadata and artifact content, supporting hybrid/semantic/lexical modes. It distinguishes itself somewhat from handover.get (which fetches a specific handover) but doesn't explicitly name the alternative. The 'empty query to list recent handovers' clarifies a key behavior.

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?

The description clarifies that an empty query lists recent handovers, giving concrete guidance on a common usage pattern. It implies when to use search (when you need to find/relevance-rank context) vs get (exact ID), but doesn't explicitly state when NOT to use it or name sibling alternatives. Reasonable context provided, no exclusions.

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