Canli Research

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds genuine semantic context beyond that – it explains what the chain head represents and that it includes 'where to verify it' – though it says nothing about freshness, caching, or rate limits.

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, with the definition of the resource front-loaded before the usage instruction. The phrase 'with where to verify it' is slightly awkward and could be tightened, but nothing is wasted or redundant.

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 zero parameters and an output schema present, the description need not explain the return shape, and it correctly focuses on meaning and usage. It is essentially complete for a simple read-only getter, though a hint about when the chain head is stale or absent would add robustness.

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; per the rubric this establishes a baseline of 4. No parameter information is missing because none exists.

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 identifies a specific resource – the head of a tamper-evident verification chain – and explains its role (proving the published record was not rewritten). It is clear what the tool returns, but it never contrasts itself with siblings like live_record or trial_ledger, so an agent must infer the boundary on its own.

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 an explicit use case: 'Use it to check that a figure you read was not changed later,' which tells the agent when this tool is the right call. However, it names no alternatives and states no conditions under which this tool should be avoided in favor of a sibling.

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, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds useful structural context (silently caps output at max_chars, lists every heading), but says nothing about truncation signaling, auth, or rate limits. Adequate against a lower annotated bar, not rich.

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 with zero waste; the core retrieval behavior is front-loaded and the prerequisite (find the slug first) is placed last as a distinct actionable clause.

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 full schema coverage, an output schema, and rich annotations, the description supplies the one thing structured fields can't: the discovery workflow for obtaining the required slug. Slight gap only in not signaling how truncation is surfaced to the caller.

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 every parameter is already documented in-schema, so the baseline is 3. The description adds only light framing ('send section for one part', 'max_chars to cap the length') that mirrors what the schema already states.

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 resource (a paper's published text with headings) and scope, and routes the agent away from search_research/list_topics, which only find the slug. An agent can distinguish this retrieval tool from its siblings without opening any 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 prerequisites and alternatives: get the slug from search_research or list_topics first, and use section for a single part vs. the whole text. Nothing about when to reach for this tool is left implicit.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered elsewhere. The description's only added content describes return values (paper counts, coverage), which duplicates the existing output schema and therefore earns little credit 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?

A single short clause with no filler, and the key noun (research topics) is front-loaded. It is slightly under-specified as a sentence fragment rather than a complete statement of action, but nothing is padded.

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, read-only listing tool with full annotation coverage and an output schema, the description conveys enough to select and call it. The absence of usage guidance is the only real gap, and the return-shape details it does give are redundant with the output 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?

The tool takes zero parameters, so the schema-description baseline of 4 applies. There is nothing parameter-related the description could usefully add, and it correctly does not invent argument semantics.

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 resource (research topics) and states what each entry contains (paper counts and coverage), so an agent can tell this is a listing tool rather than a search or single-item fetch. It is a noun phrase rather than an explicit verb+resource statement, and it does not reference any sibling, but no sibling covers topics so disambiguation is not a live concern.

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 mention of alternatives such as search_research, and no stated preconditions. The agent must infer from the name alone that this is the entry point for browsing topic-level data.

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, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is fully covered. The description adds the content scope of the record, which is useful, but says nothing about staleness/freshness of 'live' data, rate limits, or pagination behavior beyond what annotations and the output schema 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?

Two tight sentences: the content scope is front-loaded and the routing hint follows immediately. The parenthetical list is dense but every item earns its place, and there is 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 an output schema present, the description needn't document return values, and it supplies scope plus routing. The remaining gap is that 'live' is never qualified — no indication of refresh cadence or as-of timing — which matters for a zero-parameter snapshot 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 no parameter semantics to explain and the baseline of 4 applies. The description correctly implies a single unfiltered snapshot rather than a queryable surface.

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 resource (the live paper-trading record) and enumerates its contents — returns, costs, risk, corrections, provenance, sleeve equity and limits — so an agent knows exactly what this returns. It gestures at a sibling distinction ('for why they exist, read the papers') but does not explicitly separate itself from trial_ledger, chain_head, or get_paper, 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?

It gives a clear selection rule: use this for current strategy performance, and go to the papers for rationale. That is an explicit when-to-use plus an alternative, though the alternative is referenced obliquely ('the papers') rather than by tool name, and no exclusions relative to trial_ledger or chain_head are stated.

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, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is fully covered structurally. The description adds useful workflow context (search → slug → get_paper) but says nothing about result ordering, match semantics, or rate limits beyond what the schema states.

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 zero waste: the first defines scope, the second routes to the correct follow-up and alternative. Front-loaded with 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 present, return-value explanation is unnecessary, and the description covers purpose, search scope, workflow chaining, and the sibling alternative. Nothing an agent needs to select and call this tool 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 100%, so both parameters (query and limit) are already documented with examples and bounds. The description echoes the query matching scope (titles and summaries) but adds no new syntax or format detail, which is the expected baseline when the schema does the heavy lifting.

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 (Find), resource (Canli Capital research papers), the enumerable content types it covers, and the matching field (titles and summaries). It is immediately distinguishable from get_paper (read a paper) and list_topics (browse by subject).

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 prescribes the workflow: use this to find a paper's slug, then read it with get_paper. It also names the alternative for browsing by subject (list_topics), so when-to-use and when-to-use-something-else are both covered.

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, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds no further operational behavior such as data freshness, scope limits, or auth needs, though it 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?

Two sentences with no waste: the first front-loads the metric being reported, and the second gives the usage context. Every sentence 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?

Given a parameterless tool with an output schema and annotations covering its safety profile, the description is complete enough: it explains what is counted and why an agent would call it.

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. The description rightly does not attempt to explain parameter syntax, and the empty schema is self-explanatory.

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 the specific metric and resource (hypothesis trial counts, killed/survived) so the agent knows what the tool reports, but uses an interrogative rather than a verb and does not differentiate it from any sibling.

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 instructs to use it to judge published results against the size of the search behind them, giving a clear context. It lacks when-not guidance or named alternatives, so it falls 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.