INDICIA DESK

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered externally. The description adds real value by disclosing the content scope — including that it documents 'what is deliberately not available here,' which is a genuine transparency signal about limits. It stops short of saying when data was last refreshed or how to interpret the payload.

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 content topics are ordered from identity outward. It is a fragment rather than a full sentence, and the opening 'What INDICIA DESK is' partly restates the title, but nothing is wasted.

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 zero-parameter documentation tool with an output schema (so return values need no explanation) and full annotation coverage, the description is close to sufficient. The one missing element is explicit invocation guidance — telling the agent to call it at session start.

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 no parameter semantics to explain and the description correctly introduces none.

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 precisely (INDICIA DESK / this server) and enumerates the exact content it returns: identity, per-tool return values, data freshness, deliberate omissions, and plans. It is clearly distinct from the domain siblings (decision_journal, expiry_record, hypothesis_ledger, market_state), though it never states that distinction 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?

Usage is only implied — an agent must infer that this is a first-call orientation tool. There is no explicit 'call this before using the other tools' instruction, no when-not-to-use guidance, and no mention of the siblings as alternatives.

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 new behavioral facts: prices are real Deribit bid/ask, it is a paper account, and it reports only closed trades — that last point materially changes how an agent should interpret empty or small result sets.

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?

Three tight sentences, front-loaded with what the journal is and followed immediately by what it returns and then its limitation. The brand prefix is minor overhead but no sentence is wasted.

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, and the description independently signals the shape of the response (per-strategy aggregates plus latest closed trades). With light parameters and full annotation coverage, the only real omission is how the optional filters alter results.

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 67% with asset and strategy documented in the schema, while limit is documented only by bounds and default. The description contributes nothing about filtering behavior — e.g. whether asset is required for meaningful stats or how the strategy substring matches. Baseline 3 applies.

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?

Specific verb-and-resource: a decision journal of options strategies tracked at real Deribit bid/ask prices, with per-strategy trade counts, win rate, average result and latest closed trades. An agent knows exactly what it gets. It does not name or contrast the closest sibling (hypothesis_ledger), which keeps it short of a 5.

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 to show how rule-based options strategies actually performed" gives a clear selection context, and the closing line excludes a common wrong expectation (live entry signals and exact structures are unavailable). No explicit alternative tool is named, so this is strong context without full routing 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 establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds meaningful scope: hundreds of expiries, recent settled expiries, side-by-side venue comparison, current upcoming max pain, and an explicit historical-not-predictive framing.

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 description is dense but front-loaded with the core data content, then follows with usage guidance. It avoids filler, though the first sentence is long and could be split for easier scanning.

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 an output schema present, the description need not describe return values. It adequately conveys the dataset scope and the historical-vs-predictive distinction; the main remaining gap is the semantics of the limit parameter.

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 50%: asset is described as the underlying asset with an enum, but limit has no description in the schema and is not mentioned in the description. The description does not explain what limit controls, despite implying recent expiries are returned.

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 clearly identifies the resource: per-expiry max-pain settlement statistics, market-maker corridor hit rates, OI wall outcomes, recent settled expiries across Deribit/Bybit, and current upcoming max pain. It is specific and distinguishes itself from a prediction tool, but it does not differentiate from sibling tools such as market_state or hypothesis_ledger.

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 explicitly says to use this for questions like "will price pin to max pain on Friday?" and clarifies that it answers with historical hit rate rather than a prediction. That gives a clear usage context, though it does not name when to use alternatives or exclusions.

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 read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value by disclosing the return shape ('verdict status and a plain-language teaser') and an important limitation ('exact thresholds are not public'), which prevents an agent from promising precise numbers.

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?

Three tight sentences: what it is, when to use it, what you get back. The most decision-relevant facts (scope and trigger) are front-loaded with no filler.

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?

Output schema exists, so return-value detail is optional, and the safety profile is fully annotated. Minor gaps remain: it does not mention the 25-result cap or any paging behavior, which an agent querying a registry might need.

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 75% and the enums (asset, group) are already self-documenting. The description implies what the 'group' filter is for by emphasizing rejected hypotheses, and its example keywords ('max pain', 'whales') mirror the query parameter, but it adds no syntax or semantics for limit.

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?

Names a specific verb and resource ('Search INDICIA DESK's public registry of BTC/ETH market beliefs tested on its own data') and adds distinguishing scope ('including the rejected ones'). This is clearly separable from siblings like market_state or decision_journal, which do not return tested-belief verdicts.

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 states the trigger condition: 'Use when someone asks whether a popular crypto trading belief holds,' backed by three concrete example questions. It stops short of naming alternatives or when-not conditions, so it is clear but not fully routing.

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, closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts: refresh cadence of roughly two hours, the presence of an as_of timestamp, and that history depth comes from a daily archive. What's missing is any note on latency, cost, or historical window length beyond 'how long the regime has lasted'.

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 highest-value signal (gamma regime) and its interpretation, followed by supporting metrics and then the two contract sentences. The metric list is dense but every item is substantive content rather than filler; the parenthetical sign explanation is well placed.

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 an output schema present, the description needn't explain return shapes, yet it still names the key fields so an agent can judge relevance at selection time. Combined with annotations and the freshness note, an agent has enough to call it correctly; only historical window size and any error behavior are 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?

Schema coverage is 100% with a single enum-constrained 'asset' parameter documented as 'Underlying asset.' The description adds no meaning about the parameter, so the schema carries it entirely — baseline 3 is appropriate for a one-param, fully documented 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?

Enumerates the exact content returned: dealer gamma regime with sign interpretation, zero-gamma flip, call/put walls, DVOL and 1-year rank, IV-minus-RV, IV term structure, Fear & Greed, and regime duration. An agent knows precisely what data this yields without opening the output schema, and the sibling tools (ledger/journal/expiry) are unrelated enough that no differentiation is needed.

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?

States the intended stance explicitly — 'Descriptive context, not a direction call' — which tells the agent this is for contextual grounding, not trade signaling. It also gives the freshness contract (~2 hour refresh, as_of in the result). It does not name an alternative tool or say when NOT to call it, but no sibling overlaps this function.

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