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

Annotations cover safety (destructive/idempotent/openWorld), and the description goes well beyond them: shared structure/logic/dataset with text overlay, respondent language selection via ?Language=<code>, source-text fallback, seeded translation worklist, the ru/de/en-only limit on built-in service-text localization, and verification by re-reading the stored set. It even discloses the destructive edge implicitly via 'upserts translations of an existing layer'.

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?

Purpose is front-loaded in sentence one and nearly every clause carries information (fallback, ordering, service-slot limits, idempotence). It is nonetheless a dense, run-on block with caps emphasis and parenthetical asides that make it harder to scan than it needs to be.

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?

An output schema exists, so return values need not be explained, yet the description still tells the agent that the reply lists unlocalized service slot keys. Combined with auth requirements, ordering constraints and fallback behavior, an agent has everything needed to call it correctly.

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 addressing semantics the schema does not: the four translations[] item shapes ({question, text}, {question, option:<code>, text}, {question, row:<n>, text}, {target:..., text}) and the named target values. It doesn't restate the catalog-vs-unknown-code rules for direction/languageName, but those are already fully in 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?

States a concrete verb+resource ('Adds a LANGUAGE LAYER to a survey ... upserts translations') and immediately defines the domain concept (a language is a layer on the same survey, not a separate survey). No sibling tool does anything similar, so it is unambiguous which tool to pick.

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?

Explicit sequencing guidance: 'Add languages LAST', what happens to questions added after the layer, and that re-running is an idempotent upsert to pick them up. It also states the prerequisite ('Requires the edit-survey right') and the for-other-languages follow-up call, so the when/how is fully specified.

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