Zensei Index

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds genuinely non-structured behavior: the content mirrors the website FAQ wording (static reference text, not live data) and should be consulted a single time, which tells the agent this is a one-shot orientation read rather than a repeated data query.

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: the first front-loads the content scope, the second delivers the actionable instruction. No filler and no redundancy with structured fields.

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 parameters and no output schema, the description's job is to convey what the caller receives and why — it states the covered topics and, via the FAQ wording note, signals prose documentation rather than structured data. Nothing needed to call this tool correctly is missing.

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 is trivially complete, so there is nothing to document beyond the baseline. The description correctly spends no words on parameters.

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 names the resource (the Zensei Index) and enumerates what the content covers: what it is, how to read the score, how it is built, and what the server serves. It is clearly the documentation/FAQ tool and thus distinguishable in role from data-bearing siblings like zensei_index_summary or zensei_index_today, though no sibling is named explicitly.

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?

It gives an explicit usage instruction — 'Call it once before interpreting any score' — which establishes both timing (before interpreting scores) and call frequency. It stops short of naming when-not-to-use or pointing to an alternative sibling, so it is not a full 5.

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 read-only, idempotent, closed-world, and non-destructive behavior, so safety is covered. The description adds genuine behavioral context beyond that: it decodes the status vocabulary (Clear/Inactive, Watch, Stress, Activated/Danger, Calibrating, Unknown), which an agent cannot learn from the schema or annotations.

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?

It leads with what is returned, then the motivating use case, then the status legend. Every sentence carries load — the legend is the only verbose part and it substitutes for a missing enum definition in the schema.

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 output schema, the description carries the burden of describing the return shape, and it does so well (indicators, status, layer, weight, explanation). The status legend further compensates for the schema's lack of enums, leaving little an agent needs missing.

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, so the baseline is 4; there is nothing for the description to disambiguate. The absence of a date/scope parameter is worth noting but does not lower the score.

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 precisely what is returned: the ten indicators behind today's Zensei Index, each with status, scoring layer, weight, and the site-facing explanation. It is specific and distinguishable from siblings like zensei_index_summary or zensei_index_today, though it never explicitly contrasts itself with them.

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?

'Use it to explain why the index sits where it does' gives a clear selection rationale for drill-down diagnostics versus a top-level summary. It stops short of naming which sibling to prefer for aggregate views or index metadata, so no explicit alternatives or exclusions are stated.

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, so safety is covered. The description adds non-obvious behavioral context: the summary is rewritten only when indicators change, and it discloses that stale/ageDays fields exist. It does not describe the output shape, which is reasonable given no output schema exists, but leaves some ambiguity.

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-loads purpose and then adds interpretation guidance. Slightly longer than a minimal definition, but each sentence (especially the risk-scale explanation) earns its place because it changes how an agent interprets the score.

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 zero params, no output schema, and rich annotations, the description is essentially complete: it explains what the tool returns conceptually, how to detect staleness, and how to interpret the score range. Minor gap is the exact structure of the returned summary.

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?

Zero parameters, so baseline is 4. The description appropriately focuses on return-value semantics (score, regime, stale, ageDays) rather than parameters, which is correct for a no-arg tool.

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 resource (the latest written summary of the Zensei Index) and what it contains (score and regime). It distinguishes itself from zensei_index_today by noting it is the 'written summary' rather than the current number, though the boundary is soft.

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 says to check `stale` and `ageDays` before quoting, and to prefer zensei_index_today for the current number. This names the alternative and the condition that selects it.

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 cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the description's job is added semantics — and it delivers the critical non-obvious fact that this is a RISK score where LOWER IS HEALTHIER and a rising value means deterioration, plus the numeric band mapping. That prevents a plausible misinterpretation the annotations cannot address.

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 what is returned, then the essential interpretation rules, then the sibling pointer. The regime band enumeration is four clauses that consume space but carry genuine interpretation value, so it is justified rather than padding.

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?

There is no output schema, so the description carries the burden of describing the return shape, and it does so explicitly (final score, regime label, three layer scores). For a zero-argument read tool with full annotation coverage, nothing an agent needs to call and interpret it is missing.

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, so there is nothing for the description to disambiguate; baseline for a parameterless tool is 4. The description correctly avoids inventing any argument guidance.

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 names a specific resource (today's Zensei Index for U.S. equities) and enumerates exactly what the tool returns: the final score, its regime label, and three layer scores. It is clearly distinguishable from siblings, which are about/about-summary/indicator-drilldown rather than the headline daily reading.

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?

It routes the agent explicitly to zensei_index_indicators for causal drill-down ('Call zensei_index_indicators to see why the score sits where it does'). It does not, however, state when to prefer this over zensei_index_summary or zensei_index_about, so the sibling disambiguation is partial rather than complete.

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