DataSinking

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, and it does well: it discloses the token cost ('Expensive in tokens'), the exact return composition, the block-marker format for citing paragraphs, and an attribution obligation tied to the `source` field. It stops short of covering error behavior (e.g. invalid document_id) or any truncation/length limits, which keeps it out of 5 territory.

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 sentences, front-loaded with what the tool does, then routing guidance, then citation mechanics. Every sentence carries distinct information with no restatement of the schema or annotations.

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 compensates by describing the response shape (metadata + Markdown body) and the embedded block-marker structure an agent needs in order to cite correctly. For a single-parameter, single-resource fetch tool, nothing required for correct invocation 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?

Schema description coverage is 100% for the single `document_id` parameter, which already documents that the id comes from list_reports items[].id. The description adds no syntax, format, or constraint detail beyond that, so the schema does the heavy lifting — the baseline 3 when coverage is high.

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 ('Fetch one report's full text') and enumerates the payload ('metadata + Markdown body'). It also distinguishes itself from the sibling get_section by scope (full report vs one chapter), so an agent can route without opening either 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?

Explicitly names the alternative (get_section) and the condition that selects it ('when you only need one chapter'), framed against the cost of this tool. That is the exact when/when-not routing an agent needs in this sibling set.

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 discloses the output format ('annotated with block markers `<!-- ds:block:N -->`') and the cost/scope tradeoff versus get_report, which is genuinely useful. It does not mention auth requirements, rate limits, or the 404 failure mode (that detail lives in the schema).

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 compact sentences; the scope/cost contrast with get_report is front-loaded and the block-marker detail follows. 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?

With no output schema and no annotations, the description does the heavy lifting by explaining the returned content's block-marker structure and the cost rationale. It is nearly complete, missing only return-volume/auth notes, but nothing critical 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 description coverage is 100%, so the schema already documents both parameters extensively, including the cross-market keyword resolution and 404 retry guidance. The description adds no parameter-level detail beyond what the schema provides, so the 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?

States a specific verb ('Fetch') and resource ('one section of a report'), scopes it with 'by keyword', and explicitly contrasts with the sibling get_report ('much cheaper than get_report'). An agent can distinguish it from get_report and list_sections without opening either 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?

Gives clear context for when to prefer this over get_report ('much cheaper', 'best for RAG'), which is the key routing decision. It stops short of explicit when-not guidance or naming list_sections here as the alternative for discovery, though the schema's section description covers that fallback.

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, and it does meaningful work: it discloses the exact return shape (`sections` and `section_details` with title/has_tables/chars/estimated_tokens) and explains how to use estimated_tokens and has_tables. It does not state permissions or that this is a read-only, non-mutating operation, which is the remaining 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?

Front-loads the core action and the payoff (sizes before pulling), then describes the return shape and the follow-up. Slightly dense with the parenthetical aside about RAG pipelines, but nearly every clause carries actionable information.

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 correctly compensates by enumerating the returned fields and their meaning, and it links to the next tool in the workflow. Nothing needed to invoke or interpret this call 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?

Schema coverage is 100% and there is only one parameter, so the schema already documents document_id fully (including its provenance from list_reports). The description adds no syntax or format detail for it, so the 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?

States a specific verb (list) and resource (sections of a report) plus the scope (with size, in order). It is clearly distinguishable from get_section, which pulls a single chapter, and from list_reports, which enumerates reports.

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 frames the call as a prerequisite step ('before you decide what to pull') and routes the agent to the follow-up tool: 'Then call get_section with a heading keyword.' The when-to-use and the alternative are both named.

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