FAIE

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's real contribution is the semantic disclosure that the returned rank measures evidence readiness only and is not a suitability or investment recommendation. Useful framing, but it says nothing about how weak evidence is treated, whether output is deterministic, or limits beyond the 2-8 count.

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, no redundancy, with the operation and its scope front-loaded and the output caveat immediately after. Every sentence earns its place.

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 complex 8-parameter tool with no output schema and zero schema description coverage, the description omits what the response looks like, how the top-level fields relate to per-candidate overrides, and the effect of include_weak_evidence. Only the candidate-count bound is conveyed.

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% across 8 parameters, and the description only echoes the candidates count constraint (2-8) that the schema already enforces. question, crop, asset_types, horizon_days, water_source, thesis_assumptions, and especially include_weak_evidence are left entirely unexplained, including whether candidate-level fields override top-level ones.

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 ('run the same bounded FAIE evidence rubric'), the resource (candidate regions/sites), and the scope constraint (2 to 8). It is readily distinguishable from the sibling investigation tools, which operate on a single subject rather than ranking multiple candidates.

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?

Implies the use case clearly: comparing several candidates under one rubric, and it adds a crucial caveat that the ranking is evidence-readiness, not suitability or an investment call. It does not explicitly name when to prefer this over explore-style siblings (e.g., investigate_faie_evidence for a single site), so the routing guidance is contextual rather than explicit.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral constraint — that private investigation content is not exposed in the response — but says nothing about data freshness, staleness of the health snapshot, or whether a degraded result is signaled.

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?

A single front-loaded sentence with no filler, and the privacy caveat is appended after the scope rather than buried. It is suitably short for a no-argument probe, though the phrasing 'resident ... status' is slightly opaque.

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 params, rich annotations, and no output schema, the description carries the burden of saying what comes back, and it does list the three reported facets. It is close to complete; only the shape/format of those status values (e.g., pass/fail vs counts) is left unstated.

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?

The tool takes zero parameters and the schema forbids additional properties, so there is no parameter semantics to explain. Baseline 4 applies; the description correctly adds no redundant parameter talk.

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 (Return) and resource (FAIE health) and enumerates the three status facets: resident, source-health, and signal-count. It is distinguishable from investigate_faie_evidence and compare_faie_candidates, though it never explicitly contrasts itself with get_faie_signal_snapshot, which is the nearest neighbor.

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?

No when-to-use, when-not-to-use, or alternative routing is given. An agent must infer from the name alone that this is a liveness/health probe rather than the snapshot or evidence tools, and nothing tells it when a health check is preferable.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so 'Read-only and non-transactional' is a restatement of structured data rather than added context. It never explains what 'snapshot' implies for freshness/staleness or what 'public-safe' filters out, which would be genuinely new information.

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 front-loaded sentences with no filler beyond the redundant 'non-transactional' clause. Appropriately brief for a read tool, though brevity here shades into under-specification.

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?

No output schema exists and the description does not describe the returned snapshot shape, its freshness, or how `limit` shapes the result. An agent knows the tool is safe to call but not what it will receive or when to prefer it over its three siblings.

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 percent and the single `limit` parameter is never mentioned in the description. The schema supplies numeric bounds and a default but no semantic meaning for what is being limited (signals? rows? candidates?), and the prose does not compensate.

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?

The description states a clear verb (Return) and a specific resource (the latest public-safe FAIE signal snapshot). It does not, however, differentiate this tool from siblings like get_faie_health or investigate_faie_evidence, so an agent can't route between them without opening each schema.

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?

There is no when-to-use guidance, no statement of what situation calls for a signal snapshot versus the health or evidence tools. 'Read-only and non-transactional' is a trait, not usage guidance.

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

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds genuinely non-obvious behavior beyond that: public MCP investigations are ephemeral previews and are not written into the shared investigation archive, which materially affects how a caller treats the result. It still omits cost/latency and whether results are reproducible, so not a 5.

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 short sentences with no filler, and the core action is front-loaded. It loses a point because the more decision-relevant persistence caveat is buried after an undefined term, and neither "FAIE" nor "bounded" is unpacked.

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 8-parameter investigation tool with no output schema and 13% schema coverage needs far more explanation: what a returned investigation looks like, how long it runs, how the filters interact, and how it relates to the sibling tools. The description covers only ephemerality, leaving the caller under-informed.

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 13% — only "question" is documented — and the description explains none of the other seven parameters (crop, asset_types, region_keys, horizon_days, water_source, thesis_assumptions, include_weak_evidence). With low coverage, the description is required to compensate and instead says nothing about inputs.

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?

The verb+resource is present ("Run a bounded FAIE evidence investigation"), and the title supplies the domain (agriculture, land, water, production, resilience). However, "FAIE" and "bounded" are unexplained jargon, and the description never distinguishes this tool from siblings like compare_faie_candidates or get_faie_signal_snapshot. Purpose is inferable but not crisp.

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?

There is no statement of when to use this tool versus compare_faie_candidates, get_faie_signal_snapshot, or get_faie_health, and no prerequisites or exclusions. The only contextual note concerns persistence, not selection.

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