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

Annotations already declare readOnlyHint=true, but the description goes substantially beyond that: it discloses that no transaction is constructed, that the snapshot refreshes daily and snapshot_age_seconds should be read, that voter input changes target optimality, and that missing emission state flips execution_ready to false.

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 text is dense but front-loaded: recommendation shape and constraints come first, then the invocation workflow and next step. Every sentence carries operational information, though the jargon-heavy phrasing (provider-neutral, bps, Ve33) makes it slightly harder to scan than ideal.

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?

Given that an output schema exists, the description needn't explain return fields, yet it still covers the key decision points an agent needs: snapshot freshness, execution_ready gating, what to read when emission state is missing, and the exact follow-up invocation. Nothing material for correct invocation is absent.

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 cross-parameter meaning the schema cannot: combining voter with ve33_emission_state produces voter-optimal targets while preserving a neutral plan in provider_targets, and omitting the emission state changes execution readiness and local read requirements.

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 and resource: returns a provider-neutral STONX allocation recommendation with an emissions_efficiency KPI per pool and an executable target list constrained to 10,000 bps and at most 25 Ve33 pools. That level of specificity clearly separates it from siblings like get_ve33_allocations and prepare_ve33_reallocation.

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 explains the two calling modes (with or without voter/ve33_emission_state) and the resulting output differences, including that execution_ready is false without the emission state. It also names the exact follow-up path: require execution_ready=true, then pass targets plus state_id from get_ve33_allocations and strategy=compact_max_lock to prepare_ve33_reallocation.

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