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

Annotations already say readOnly/non-destructive, and the description adds genuine domain behavior beyond that: each row is one leg, a move produces both a send-transfer (already completed) and a receive-transfer (in-transit until confirmed). It also discloses a real limitation — search matches transfer number and invoice only, not product names — that would otherwise cause failed queries.

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 purpose and tightly packed; nearly every sentence carries distinct information (leg model, type definitions, search limitation, line-item gap). The clipped, fragment-heavy style is efficient but slightly dense for a first read.

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 read-only, six-parameter list tool with a fully documented schema and no output schema, the description covers the gaps an agent would hit: what a row represents, why counts may seem doubled, what search cannot do, and where to go for details.

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 the baseline is 3, but the description adds meaning beyond the schema: it disambiguates the 'in-transit' status value, constrains what 'search' actually matches, and defines the non-obvious enum values 'receive-stock' and 'bulk-edit'. It does not address pagination or the outletIds filter specifically.

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+resource ('The Stock Transfers list') and immediately frames the questions it answers ('what transfers are open', 'what is still in transit'), so an agent knows exactly what the tool is for. It also distinguishes itself from the detail sibling by noting that rows carry no line items and that get_stock_transfer opens a single transfer.

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 when-to-use guidance: filter status 'in-transit' to find open work, and use get_stock_transfer instead when line-level detail is needed. It also pre-empts confusion by explaining that 'receive-stock' is supplier stock and 'bulk-edit' is a recount, which are not transfers to chase.

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