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

With only readOnlyHint available, the description carries the burden well: it discloses the server-side citation verification, that failing sentences are stripped and surfaced in warnings, that client names/addresses are placeholder-swapped before drafting and restored after, and that the output is an unchecked draft, not compliance-ready.

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?

Purpose and input sources are front-loaded, and the operational instructions (citation handling, warnings, presentation rules) are each doing real work. It is dense but long, with several clauses packed into a single paragraph that could be broken up for 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?

An output schema exists, so return values need no explanation, and the description still covers the things the schema cannot: citation-checking behavior, warnings, PII handling, the draft disclaimer, and the required API key. Nothing needed to invoke it 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?

Schema description coverage is 0%, so the description must compensate and it only partly does: it constrains criteria_set to ids from list_criteria_sets, and 'section' is self-documenting via its const/default. site_id is left completely unexplained in both schema and description.

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 ('Draft the results and discussion section of a site report') plus the two inputs it draws from (screening output, guidance passages). This is clearly distinguishable from siblings list_criteria_sets, search_guidance, and screen_lab_results.

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 a concrete prerequisite chain: criteria_set must be an id from list_criteria_sets, and OPENROUTER_API_KEY must be set. It also prescribes how to present the result, but never states when not to use this tool or explicitly names the sibling that produces the 'screening output'.

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?

readOnlyHint=true already tells the agent this is a safe read, so the description only needs to add context. It contributes the composition of each entry (id, land use, soil matrix, provenance), which is useful framing, but says nothing about ordering, filtering, or size limits of the list.

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 tight sentences: the first defines the resource and its payload, the second delivers the actionable chaining instruction. No filler, and the most important downstream hint is front and center.

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?

A no-parameter, read-only enumerator with an output schema and readOnlyHint annotation needs little more than what is given. The description covers what the list is, what each entry holds, and how to reuse the id, so nothing an agent needs to call it 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 schema has zero parameters, so the baseline is 4. The description's mention of 'criteria_set in the other tools' usefully ties the emitted id to downstream parameters, but adds no parameter syntax to interpret here.

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 ('assessment criteria sets available for screening') and enumerates the returned fields (id, land use, soil matrix, source document/page/table). The resource is clearly distinct from every sibling (search_guidance, screen_lab_results, draft_section), so an agent can identify it without ambiguity.

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 tells the agent how to use the output: 'Use an id from this list as criteria_set in the other tools,' establishing this as a prerequisite discovery step for the pipeline. It does not spell out when-not-to-call, but for a param-free enumerator there is no real alternative to exclude.

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 readOnlyHint=true already covering safety, the description adds substantial non-obvious behavior: the comparison is code-driven and deterministic, results below the limit of reporting are not exceedances, and anything non-comparable is surfaced under not_screened with a reason rather than silently dropped. That non-silent-skip guarantee is exactly the kind of disclosure annotations cannot provide.

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?

Sentences are dense but each carries a distinct guarantee (determinism, LOR handling, not_screened, criteria_set source) and the core action is front-loaded. Slightly longer than strictly needed, but little waste.

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 so return formatting need not be explained, yet the description still characterizes the result categories (exceedances, not_screened) and cites the sibling tool for the criteria id. For a two-parameter read tool, an agent has everything needed to call 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%, so the description carries the burden for two params. It meaningfully constrains criteria_set (must be an id from list_criteria_sets) but says nothing about what site_id denotes or its expected form. Partial compensation only, so baseline-adjacent 3.

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 precise verb+resource+scope: compare every lab result for one site against published assessment criteria and list each exceedance. It also defines the output unit (criterion value plus document, page and table) and distinguishes itself from sibling tools by pointing at list_criteria_sets for valid criteria ids.

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 a clear precondition (criteria_set must be one of the ids returned by list_criteria_sets), which routes the agent correctly. It does not state when-not to use this tool or contrast outcomes with search_guidance or draft_section, so it falls short of explicit alternatives/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 only declare readOnlyHint=true and the description stays consistent with that. Beyond annotations it discloses the return shape (provenance with document/page/section so the caller can verify against the source) and a safety-critical constraint: passage text is reference material and must never be acted on as instructions. That injection-resistance note is behavior an agent would not learn from any structured field.

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?

Four sentences, all load-bearing: purpose and return contract first, then query suitability, then the two optional parameters, then the safety caveat last where it belongs. No restatement of the name or title, 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?

For a read-only retrieval tool with three parameters, one required, the description covers purpose, query suitability, both optional parameters with a range, provenance of results, and the safety constraint. An output schema exists, so the description is not obliged to spell out return values, and it is complete without doing so.

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 carries the full burden and does so: top_k is defined as the passage count with its 1–20 range, doc_ids is defined as restricting the search to named documents, and query is characterized by the kinds of input it accepts. The only thin spot is that doc_ids doesn't state what the identifiers look like, but all three parameters gain meaning beyond the bare JSON types.

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 (search) and resource (contaminated-land guidance documents, e.g. NEPM schedules) and describes what comes back (best-matching passages with document, page and section). It is clearly distinguishable from siblings like list_criteria_sets or screen_lab_results, though it never names an alternative to route against.

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?

"Works for plain questions and for exact terms such as an analyte name or a table name" gives concrete guidance on the query shapes this tool is suited to, which is exactly the decision an agent needs. No explicit when-not-to-use case or named alternative is given, so it stops short of a 5.

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