Seiche Market Atlas Corpus

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

With no annotations, the description carries the full burden, and it does disclose one meaningful boundary: this tool returns inventory only, and binary payloads are not served here. It omits other behavioral traits an agent would want, such as read-only nature, whether the flow must already exist, and whether results are paginated or cached.

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?

One compact sentence with the outcome front-loaded and no filler; nothing is repeated from the name or schema. Density from terms like 'content-addressed' costs a little readability but there is no wasted text.

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 and no annotations mean the description must explain the manifest's shape and the flow_id input, and it does neither. An agent knows the tool exists and that binaries come from REST, but not what a 'shard inventory' record contains or what identifier to supply.

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 single parameter flow_id has 0% schema description coverage and is not mentioned anywhere in the description, so its meaning and expected format are undocumented in both places. The sentence focuses on the return payload rather than the input needed to invoke the 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?

Names a specific verb ('Discover') and resource ('BIS shard inventory') scoped as a manifest, which separates it from bis_observations and bis_records (data fetchers) among the siblings. The phrasing 'content-addressed BIS shard inventory' is jargon-heavy, so an agent gets the gist but not a crisp plain-language statement of what comes back.

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?

'binary shards remain REST downloads' implies the intended workflow: use this tool to discover the inventory, then fetch binaries out-of-band via REST. That is useful when-not guidance, but there is no explicit statement of when to pick this over the sibling bis_* tools or any prerequisites for making the call.

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?

No annotations are provided, so the description carries the full disclosure burden. 'Read' weakly implies a safe read operation and 'bounded' hints at a result cap, but 'revision-aware' is never explained, and nothing is said about permissions, pagination, rate limits, or what a revision-aware read actually returns.

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 is a single front-loaded sentence with no wasted words, which is structurally clean. The terseness, however, reads as under-specification rather than disciplined concision given the total absence of supporting detail.

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, no annotations, and zero parameter documentation, the description needs to explain the return shape, the meaning of revision-awareness, and how to supply a flow_id. None of that is present, leaving the agent materially under-informed for a tool with a required identifier 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 description coverage is 0%, so the description must compensate and does not. 'flow_id' is never explained (what a flow is, its format, where to obtain it), and 'limit' is only obliquely referenced by the word 'bounded' rather than tied to the 1-1000 range or default behavior.

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 specific verb (Read) and resource (BIS observations), which is better than a tautology. However, the modifiers 'bounded' and 'revision-aware' are unexplained jargon, and it gives no signal to distinguish this from siblings like bis_records or seiche_observations.

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 guidance on when to use this tool versus bis_records, bis_flow_manifest, or seiche_observations, and no prerequisites or exclusion conditions are stated. The agent is left to infer everything from the name alone.

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?

No annotations are provided, so the description carries the full burden. It does disclose one meaningful behavioral trait beyond the schema: results are "bounded" and complete data requires the manifest/shard path. It omits pagination mechanics, permissions, and what "bounded" concretely means, leaving significant gaps for a no-annotation tool.

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 padding; the browse action comes first and the alternative path second. It is dense with unexplained terminology, 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?

No output schema and no annotations, so the description must carry the full load, and it does not: pagination behavior, record contents, auth needs, and the meaning of flow_id/limit/cursor are all unaddressed. For a three-parameter data-retrieval tool, this leaves the agent under-equipped to invoke 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 description coverage is 0% across three parameters (flow_id, limit, cursor). The description only loosely implies bounding, which weakly maps to limit/cursor, and says nothing about what flow_id identifies. With the schema silent and the description not compensating, the agent must guess at all three 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?

States a verb ("Browse") and a resource ("BIS records") and qualifies it as "bounded" and "full-fidelity", which hints at how it differs from bis_observations and the manifest tool. However, "BIS" and "full-fidelity" are undefined jargon, so the agent cannot fully tell what record type this returns versus its siblings.

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?

The clause "use the flow manifest and shard URLs for complete transfer" effectively says when not to use this tool, routing the agent to the bis_flow_manifest sibling for full transfers. It gives clear context for the bounded-browse case, though it does not name the sibling tool explicitly or state prerequisites like a valid flow_id.

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?

With no annotations at all, the description carries the full behavioral burden. 'Summarize' implies a read-only aggregation, but the description never states that nothing is mutated, whether this is expensive, or that it returns a catalog-wide rollup rather than per-corpus detail. Coverage is minimal for a tool with zero annotation support.

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; the scope qualifier ('every registered corpus and evidence class') immediately follows the verb. 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 no-argument tool this is close to sufficient, but with no output schema the description should hint at the shape of the summary (counts, names, status) so the agent knows what it will receive. Domain terms like 'evidence class' are also left undefined.

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 no parameters, so there is no parameter semantics to describe and nothing for the description to compensate for. Baseline 4 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?

The description names a specific verb ('Summarize') and a clear scope ('every registered corpus and evidence class'), so an agent understands it is an aggregate inventory operation. It does not, however, distinguish itself from the sibling 'corpus_health' or explain how a summary differs from a listing.

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 indication of when to call this versus 'corpus_health', 'list_datasets', or 'inspect_dataset', all of which appear to be adjacent catalog/metadata tools. No prerequisites, no exclusions, no 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?

With no annotations, the description carries the full burden of behavioral disclosure, and it provides almost none. It does not say whether the call is read-only, whether it hits external services, whether it can be slow or rate-limited, or what an unhealthy result looks like.

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 short sentence with no padding, front-loaded with the action and the two things checked. It is efficient, though it is arguably under-specified rather than truly concise.

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?

The tool is simple (no params, no nested objects), but there is no output schema and no annotations, so the description is the only source of information about what 'check' returns. It never states the shape or meaning of the result (e.g. status per root), leaving a meaningful gap for a diagnostic tool.

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 clarify beyond what the empty schema already conveys. Baseline 4 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?

The description names a verb ('Check') and two resources ('corpus service and storage roots'), so an agent can tell it is a health probe rather than a data-returning tool like corpus_catalog. However, 'check' is vague about what is actually verified or returned, and it does not explicitly differentiate itself from the sibling catalog/dataset tools.

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 call this tool versus alternatives, no mention of prerequisites, and no indication of whether it should be used as a diagnostic before other corpus operations. Usage must be inferred entirely from the name.

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?

With no annotations, the description carries the full behavioral burden. It discloses one real trait — that inspection does not touch raw storage — but says nothing about read-only guarantees, permissions, latency, or what the inspection returns.

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; efficient, though its terseness borders on under-specification rather than pure conciseness.

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 read tool with no annotations and no output schema, the description should at least say what 'inspect' yields and where valid dataset_ids originate. Both are missing, leaving an agent unable to predict results or discover the input.

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%, so the description must compensate. 'One canonical public-index dataset' does clarify what dataset_id refers to, but adds no format, provenance, or hint that IDs come from list_datasets.

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 gives a specific verb (inspect) and resource (one canonical public-index dataset), so an agent knows this reads metadata rather than listing. It does not differentiate itself from siblings like corpus_catalog or list_datasets, so scope remains partly ambiguous.

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 explicit when-to-use guidance and no named alternative. The phrase 'without reading raw storage' gestures at a lightweight-metadata use case but never says which sibling to prefer instead or under what conditions.

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?

No annotations are provided, so the description carries the full behavioral burden. It does not confirm the read-only nature, explain pagination behavior implied by the cursor parameter, or clarify what 'rights' and 'product eligibility' mean for the returned records.

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 sentence with no filler, so it is not bloated. However, the brevity stems from under-specification rather than discipline, and the 'rights and product eligibility' clause is ambiguous rather than informative.

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-filter catalog listing with no annotations, no output schema, and no parameter documentation needs far more than one sentence. Nothing about filtering semantics, pagination, or result shape is conveyed, leaving the definition inadequate for correct invocation.

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?

All 8 parameters have 0% schema description coverage, and the description names none of them. Filters like group, engine, data_class, collection_kind, publication_state, and acquisition_review are entirely opaque, so the agent has no basis for constructing a correct call.

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 ('List ... datasets') is clear, but the qualifier 'with rights and product eligibility' is unexplained jargon and the description never distinguishes this from siblings like inspect_dataset or corpus_catalog. An agent knows the general action but not how this listing differs from the other catalog tools.

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 prerequisites, and no mention of alternatives such as inspect_dataset for a single dataset. The agent is left to infer that this is the enumeration entry point for the catalog.

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?

No annotations are provided, so the description carries the full behavioral burden. "List" implies a read-only enumeration, but the description says nothing about return shape, pagination, ordering, or what "normalized" means operationally. For a zero-annotation tool this is a significant transparency gap.

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 terse sentence with no filler or repetition. It is efficient, though the brevity borders on under-specification rather than true conciseness.

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, no parameters, and no annotations, the description is the only source of information — yet it never explains what the listed "coverage" actually contains or how results are structured. An agent cannot predict the response, so the definition is incomplete for even a simple listing tool.

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 at the parameter level. The baseline for a parameterless tool 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?

"List normalized Seiche money-market coverage" gives a verb (List) and a resource (Seiche money-market coverage), so the basic action is identifiable. However, "normalized coverage" is vague — it does not say whether this returns markets, instruments, or a coverage map, and it does not differentiate from siblings like seiche_observations or list_datasets. Purpose is implied rather than concrete.

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 the many sibling listing tools (corpus_catalog, list_datasets, seiche_observations). No prerequisites, no context, no alternatives named. The agent must infer usage from the name alone.

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?

With no annotations, the description carries the full burden. 'Read' implies a non-mutating operation and 'bounded' hints at limit/pagination, but there is no disclosure of return format, cursor behavior, permission requirements, or what 'canonical' versus redistribution validation actually means for results. Significant behavioral gaps remain.

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, which is structurally tidy. But the density of unexplained domain jargon ('canonical', 'source-wide redistribution validation') means the brevity comes at the cost of comprehension rather than earning 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 an 11-parameter, 2-required-parameter tool with no annotations and no output schema, a single jargon sentence is inadequate. Nothing explains the partition filters, time windows, or quality/staleness selectors needed to invoke 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 description coverage is only 9% across 11 parameters, so the description must compensate and it does not. It explains none of market, source, quality, staleness, event_from/to, knowledge_at, instrument_id, cursor, or semantic_role; only 'bounded' loosely gestures at 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?

States a verb ('Read') and resource ('canonical Seiche rows'), so it is more than a restatement of the name. However, 'source-wide redistribution validation' is opaque jargon and the description does not differentiate this tool from siblings like bis_observations, corpus_catalog, or seiche_markets. An agent gets a rough sense of a read tool but not of what makes it distinct.

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?

The phrase 'after source-wide redistribution validation' faintly implies a precondition, but it is never stated as when-to-use or when-not-to-use. No alternatives (e.g., bis_observations) are named, so the agent has no routing guidance.

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