Jemeen Agent Services

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds genuinely new behavioral context: it performs live network fetches, caps them at 10 URLs, limits to one public domain per call, and returns a 0-100 score plus per-check evidence and prioritised fixes. It does not discuss failure modes (unreachable domain, redirects, timeouts) or latency, which keeps it from a 5.

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: the first front-loads what is audited with a dense but scannable enumeration of checks, the second covers outputs and tier limits. The check list is long but each item maps to a real capability, so little is wasted; a slightly tighter phrasing could improve it.

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 return shape (0-100 score, per-check evidence, prioritised fixes), and with only one well-documented parameter and clear annotations, there is nothing an agent needs to call this correctly that 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% for the single `domain` parameter, so the baseline is 3; the description adds a meaningful constraint beyond the schema by specifying it must be a *public* domain and that only one domain per call is allowed. The schema already supplies the accepted format (domain or https URL, e.g. example.com), so no further gain is available.

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 (audits) and resource (a domain's discoverability/usability for AI assistants and autonomous agents), then enumerates the concrete artifacts checked (robots.txt AI crawlers, llms.txt, sitemap, JSON-LD, A2A Agent Card, MCP/OpenAPI, x402). The sibling tools (csv_quality, extract_requirements, validate_json, verify_citations) are unrelated utilities, so no sibling disambiguation is needed.

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?

Implicitly clear scope — use it to audit a public domain's AI readiness — and it states a hard operating constraint (one public domain per call, at most 10 URLs fetched), which bounds when it is appropriate. It does not name alternatives or explicitly exclude cases (e.g., private/intranet domains), 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.

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

Beyond the readOnlyHint and openWorldHint annotations, the description adds important behavioral details: the report is deterministic, no model calls are made, no data is retained, and there are explicit size limits (5 MB paid / 200 KB free). These disclosures materially help an agent understand privacy, cost, and operational constraints.

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 and report contents, followed by concise behavioral and size-limit notes. Every sentence contributes useful information and there is no filler or redundant restatement.

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?

Although there is no output schema, the description explains the report contents (row-level examples and recommended fixes) and the operational boundaries (deterministic, no data retained, size limits). Combined with complete parameter documentation and read-only annotations, it gives an agent enough information to invoke 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 100%, so the input schema already documents the csv, delimiter, and hasHeader parameters. The description does not add syntax or format guidance beyond the schema, so the baseline score of 3 is appropriate.

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 resource (CSV file) and a specific output (deterministic quality report), then enumerates the exact checks included: structural errors, ragged rows, inferred types, blanks, invalid emails/URLs/phones, duplicates, and candidate keys. This distinguishes it from siblings such as validate_json and verify_citations, which target different resources.

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 context implies this tool is for assessing CSV data quality, but there is no explicit when-to-use/when-not-to-use guidance and no routing among sibling tools. It supplies size limits, which helps set expectations, but an agent must infer that this is the right tool for CSV quality versus, for example, JSON validation.

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?

Beyond the readOnlyHint/openWorldHint annotations, it discloses determinism ('no model calls'), the size ceiling that gates the call (500,000 chars paid / 30,000 free), and the exact shape of each returned item including character offsets and section headings. Those are precisely the traits an agent needs before committing a large document.

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 dense sentences, front-loaded with what is extracted and followed by provenance guarantees, determinism, limits, and input format. Nothing repeats the tool title or the schema, and each sentence adds a decision-relevant fact.

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, and the description compensates fully by describing the returned fields (offsets, section headings, dates, money, percentages) and the provenance guarantee. Combined with the stated input constraints and determinism, 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 coverage is only 50%, so the description must carry weight for the undocumented 'text' parameter — and it does, specifying plain-text-only input and the character limits that constrain its value. The optional 'source' label is left to the schema, which already documents it, so the gap is minor.

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 (extracts) and enumerates the exact resource classes it returns: obligations, prohibitions, recommendations, deadlines, submission instructions and evaluation criteria, plus the input domain (tender, RFP, contract, policy text). This is clearly distinguishable from siblings like verify_citations or validate_json, which operate on outputs rather than source documents.

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 input precondition — 'Plain text input; convert PDFs first' — and states capacity limits that determine whether a call is viable. It does not name alternatives or state when not to use it versus verify_citations, which is the natural downstream step, so it stops short of the top band.

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 openWorldHint=false, so safety is covered by structured data. The description still adds real context beyond that: full error enumeration with instance path, schema path and plain-language message, plus the 1 MB combined (100 KB free tier) size limit that would otherwise cause surprise failures. It doesn't say what happens when the schema itself is invalid, which keeps it below 5.

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 capability, then use case, then constraint. No filler; each sentence adds distinct information an agent needs.

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 correctly discloses the return shape (every error with both paths and a message), and it discloses the size limit. The only gap is edge-case behavior, e.g. invalid or unresolvable $ref schema input, which an agent might want to know before relying on it as a gate.

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 the burden. It identifies the two inputs conceptually ('JSON document' and 'JSON Schema') and adds the combined 1 MB / 100 KB size constraint, but never clarifies that data accepts any JSON type while schema must be an object, nor the parameter names.

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 (validates a JSON document against a JSON Schema) and scopes it precisely to core 2020-12 keywords including $ref/$defs, anyOf/oneOf/allOf and formats. That level of specificity clearly separates it from siblings like agent_readiness, csv_quality or verify_citations.

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?

"Use it as an independent gate on structured LLM output before acting on it" gives a concrete trigger and position in the workflow. It doesn't name an alternative tool or state exclusions, but for this tool family there's no close competitor that needs routing away from.

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 cover readOnly and openWorld, and the description adds real behavioral detail: the four outcome statuses, per-claim results with passage/offset/hash/fetch time, plus concrete constraints (20 claims paid / 3 free, public http(s) only, 2 MB per page). The free-tier limit wording is slightly ambiguous about which tier applies, keeping it from a 5.

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 dense sentences: action, return shape, motivation, then constraints. Front-loaded with the core operation and 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, the description fully covers return structure (statuses, source passage, character offset, HTTP status, content hash, fetch time) as well as quotas and scope limits. An agent has everything needed to call and interpret 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?

Schema coverage is 0%, but the single param is a self-explanatory claims array of {id, url, quote}, and the description reinforces the quote/url pairing and adds the meaningful per-call claim limit. The role of the optional id field is left unstated.

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 — fetches each cited URL and checks whether quoted text appears — and is unmistakable against siblings like validate_json or csv_quality. An agent knows exactly what operation this performs.

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?

"Catches hallucinated or drifted citations before an agent relies on them" gives a clear trigger condition, and the quoted-text framing implies it is for citation claims, not general URL checking. It stops short of naming when-not or an explicit alternative tool.

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