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

The description uses the verb 'build', which typically implies creating or modifying state, directly contradicting the readOnlyHint annotation. This contradiction is significant and could mislead an agent about the tool's side effects.

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 a single sentence that is concise and to the point, avoiding unnecessary verbosity. It conveys the core idea without extra fluff, though it sacrifices clarity for brevity.

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 the tool's composite nature (building a research object from multiple resources), the description lacks essential details such as input/output structure, how it interacts with other tools, or what the resulting object looks like. It is incomplete for an agent to use effectively.

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 two parameters (topic and cutoff_date) with no descriptions, and the description itself provides no explanation of them. With 0% schema coverage, the description fails to compensate, leaving the meaning and expected values of the parameters unclear.

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 the tool builds a traceable cross-institution research object with claim/report counts and mixed directions, giving some specificity. However, it is vague about the exact output format and what 'mixed directions' implies, leaving room for 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?

The description provides no guidance on when to use this tool versus the sibling tools such as search_research_reports or verify_thesis. It does not mention prerequisites or scenarios where this tool is the appropriate choice.

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 readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds meaningful behavioral context by specifying that the calculation is based solely on local prices and deliberately does not validate fundamentals, disclosing a limitation beyond the 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?

The entire description is one tight sentence with no wasted words. The key capability and resource are front-loaded, and the caveat is a compact second clause that earns 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?

With 4 parameters, zero parameter descriptions, and no usage guidance, the context is incomplete despite the output schema covering return shape. An agent would still lack date format, benchmark semantics, and when to prefer this over sibling research tools.

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 needed to compensate for undocumented parameters, but it does not explain ticker, start_date, end_date, or benchmark semantics or formats. The only related detail is the mention of 'local prices,' which does not map to any parameter.

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 opens with a specific verb ('Calculate') and names concrete outputs ('return, volatility and drawdown') plus their data source ('local prices'). This clearly separates it from qualitative siblings like search_research_reports, verify_thesis, and build_research_object, and the closing caveat adds precision about scope.

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 description implies when the tool is appropriate (compute market metrics from local prices) and offers a negative signal ('prices do not validate fundamentals'), but it never names alternatives or states a concrete when-to-use/when-not-to-use decision rule. This is useful but not explicit 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?

The description explicitly says 'Read', which aligns with the readOnlyHint annotation. It adds valuable context about what specific corpus information is being read (coverage, topics, cutoff, mode), going beyond the annotation's simple read-only designation.

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 a single concise sentence that efficiently communicates the tool's function and timing. No filler or redundant information is present.

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 that an output schema exists, the description does not need to detail return values. It provides sufficient context about what the tool reads and when to use it, making it complete for its purpose.

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?

There are no parameters, so the baseline score of 4 applies. The description does not need to explain parameters, and it appropriately focuses on the tool's purpose rather than parameter details.

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 states the action (Read) and the specific resource (corpus) with explicit attributes (coverage, topics, cutoff, synthetic/live mode). It effectively distinguishes this tool from siblings like list_theses or search_research_reports by focusing on corpus metadata rather than content retrieval.

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 'before research' provides a clear temporal usage context, indicating this tool should be used as a preliminary step. While it does not explicitly name alternative tools, the instruction to read corpus information before conducting research implies when to use this tool versus other search/list tools.

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 readOnlyHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds a topic-scoping constraint but discloses no additional behavioral traits such as pagination, filtering behavior, or interaction with evidence sources.

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 a single concise sentence with the primary action and resource front-loaded. It wastes no words, but the listing of 'IDs, dimensions and report evidence' is somewhat awkwardly packed into the sentence.

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 presence of an output schema reduces the need to explain return values, and the description covers the core listing intent. However, the important cutoff_date parameter is unexplained, and the meaning of 'report evidence' and 'dimensions' is left vague, so an agent may not know what to expect beyond the schema.

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 for the two undocumented parameters. It only reinforces that the tool works for 'one topic,' which maps to the topic field, but it entirely omits the cutoff_date parameter and its meaning.

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 clear action ('List') and a distinct resource ('structured investment theses') with a specified scope ('for one topic'). It differentiates this from search-oriented siblings by focusing on theses rather than reports or news, though the phrase 'IDs, dimensions and report evidence' is slightly ambiguous about what exactly is returned.

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 description provides no guidance on when to use this tool versus alternatives like search_research_reports or read_evidence. It only implies that the tool works for one topic, without stating exclusions, prerequisites, or preferred scenarios for sibling tools.

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 readOnlyHint and non-destructive behavior, so the description only needs to add context. It adds the research-cutoff bounding and the filesystem-path exclusion, but it does not disclose error handling, missing-ID behavior, or return format details. This is a modest addition beyond the 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?

Two tightly packed sentences with no filler. The main operation and resource are front-loaded, followed by a relevant boundary statement. Every word contributes value.

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 simple read-by-ID tool with readOnly annotations and an output schema, the description covers the essential elements: what is read, how it is identified, and an important boundary. It could be more complete with explicit alternative routing or edge-case behavior, but those are not critical for invoking the tool 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 must carry parameter meaning. It effectively does so: 'by ID' maps to chunk_id and 'bounded by the research cutoff' maps to cutoff_date. It gives both parameters semantic roles, though it omits format details or constraints.

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 a specific resource ('known corpus chunk by ID'), and the 'No filesystem paths' exclusion further narrows what it operates on. This clearly distinguishes it from the sibling search and verification 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 explicit guidance on when to use this tool versus siblings like search_research_reports or verify_thesis. The 'No filesystem paths' note provides a negative constraint, but the description does not say 'use this when you have a known chunk ID' or direct the agent to alternatives for discovery.

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=true and destructive=false, so the description does not need to repeat that. It adds no further behavioral details (e.g., rate limits, pagination, or result ordering), but does not contradict the 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?

A single, compact sentence conveys the core functionality without extraneous wording. It is well-structured and easy to parse.

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 straightforward, and the existence of an output schema means return-value details need not be in the description. The description covers the essential purpose and scope, though it omits any mention of edge cases or result handling.

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 covers 4 parameters but the description explains none of them individually. It only hints that start_date and cutoff_date relate to 'publication dates'. This is minimal compensation for zero schema coverage, leaving query and top_k semantics unexplained.

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 states the action ('Search'), the target ('news AND company announcements'), the constraint ('within publication dates'), and a distinctive feature ('including adverse evidence'). It distinguishes this tool from siblings like search_research_reports and read_evidence.

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?

No explicit guidance is given for when to use this tool versus alternatives like search_research_reports or read_evidence. The description implies it is for news/announcements but does not state scenarios or contrast with other search tools.

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 mark this as read-only and non-destructive, so the safety profile is covered. The description adds useful return-semantic context (exact evidence, provenance, evidence_set_id), but it does not explain ranking behavior, how cutoff_date affects results, or any limitations beyond the structured 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?

Two short sentences with no wasted words. The action is front-loaded and the return value is stated immediately. It is concise without sacrificing the core purpose.

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 and read-only annotations present, the description does not need to detail return values or safety. However, given the sibling tools and the three parameters with no schema descriptions, the description is missing enough guidance about when to choose this tool and how to use parameters like cutoff_date to be fully complete.

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%, and the tool description does not explain query, top_k, or cutoff_date semantics. The parameter names are somewhat self-explanatory, but the description adds no meaning beyond the schema and leaves query construction and cutoff behavior entirely implicit.

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 states a specific verb and resource: 'Search original research reports.' The phrase 'original research reports' distinguishes this tool from siblings like search_news and list_theses, and the return note (exact evidence, provenance, evidence_set_id) sharpens its purpose.

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 description implies the tool should be used when original research evidence is needed, but it does not explicitly say when to use this tool versus alternatives like search_news or list_theses. No exclusions or alternative routing are provided.

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 convey read-only and non-destructive behavior, and the description adds useful behavioral context: validation is limited to schema compliance and exact quotes, insufficient answers must have low confidence with empty citations/findings, and semantic entailment is not evaluated. This goes beyond the structured hints and prevents misuse.

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 front-loaded with the core purpose, then uses a clear structured list for the required answer fields, and ends with an important limitation. Every sentence earns its place with no redundant 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 validation tool with nested objects and minimal schema descriptions, the description covers the answer schema, the meaning of evidence_set_ids, the insufficient-answer convention, and the scope of validation. Since an output schema exists, the missing return-value details are not a significant gap.

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?

Despite 0% schema description coverage, the description thoroughly documents the answer parameter's required nested structure, including confidence values, citations fields, and findings fields. It also clarifies that evidence_set_ids refer to 'previously returned evidence sets' and ties validation to 'one cutoff,' providing essential meaning the schema lacks.

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 opens with a specific verb and resource: 'Validate answer schema and exact quotes against previously returned evidence sets.' It clearly states what the tool does and differentiates it from semantic checks by noting it 'does not prove semantic entailment.'

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 description clearly implies when to use the tool: when validating a research output against previously returned evidence sets. The caveat that it does not prove semantic entailment gives a helpful boundary, though it does not explicitly name sibling alternatives or provide explicit when-not-to-use guidance beyond that limitation.

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 readOnlyHint=true and destructiveHint=false, and the description's 'retrieve' wording is consistent with that. It adds useful context about separating facts, expectations, and prices, but it does not explain mechanics such as how cutoff_date affects the retrieval or what 'verify thesis dimensions' concretely entails.

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 a single compact sentence with front-loaded action and useful output categories. It avoids fluff, though the phrase 'verify thesis dimensions' is somewhat vague and could be clearer without adding length.

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 has annotations and an output schema, which lowers the burden on the description. However, the description leaves ambiguity around when to use this tool versus siblings and does not clarify cutoff_date semantics, making it only minimally complete 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?

Schema description coverage is 0%, so the description must compensate for the lack of parameter documentation. It does not explain thesis_id beyond what the schema shows, and cutoff_date's role is only vaguely hinted at by 'subsequent events'. This is insufficient for a 2-parameter tool with no schema descriptions.

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 action ('retrieve subsequent events') and resource ('thesis'), and adds meaningful output detail ('separate facts, expectations and prices'). It does not explicitly distinguish itself from sibling tools like read_evidence or validate_research_output, so it falls 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?

The description implies the tool is for verifying a thesis using subsequent events, but it never states when to prefer this tool over alternatives such as read_evidence or validate_research_output. There is no explicit usage context or exclusion criteria.

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