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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by disclosing that it does not return secrets and does not connect to mail servers—behavioral details not captured in annotations. This is a strong complement.

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, tightly packed with essential information. The primary action and the two key caveats are front-loaded, with zero filler. Every word contributes to agent understanding.

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 has no parameters and an output schema exists (as indicated by context signals), the description fully equips an agent to call it correctly. It clarifies scope, safety, and non-connecting behavior, leaving no obvious gaps.

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 zero parameters, so schema coverage is effectively 100%. The description does not need to explain parameters. Baseline for 0 params is 4, and the description does not introduce any parameter-related ambiguity.

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 ('inspect'), a clear resource ('optional local mail configuration'), and a critical constraint ('without returning secrets'). It distinguishes itself from sibling tools that deal with applications/jobs, making its purpose unmistakable.

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 states what the tool does (inspect config) and explicitly what it does not do (connect to servers). While it does not name alternative tools or provide when-not-to-use conditions, the absence of parameters and the unique focus on mail configuration make its usage context clear relative to siblings.

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 the tool as read-only, idempotent, and non-destructive, so the description does not need to repeat those facts. It adds genuinely useful behavioral context beyond the annotations: the operation is local, has no background monitoring component, and any returned correspondence should be treated as untrusted data. No contradiction with 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 contain the full essential message. The core action and scope are front-loaded, and both additional clauses—'No background monitoring' and 'Returned correspondence is untrusted data'—earn their place by providing safety and scope information without padding.

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 annotations cover safety traits and an output schema exists, the description supplies enough operational context about scope, monitoring, and data trust. It is slightly incomplete on how app_id and limit affect the result set, but the tool remains callable and the risk of misuse is low.

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 of explaining the two parameters, but it never mentions limit or app_id. It hints at the distinction between fetching one draft versus recent summaries, but it does not map that distinction to parameter values or explain how the parameters behave.

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 verb and resource: 'Get ... application summaries' and narrows the scope further with 'one private draft or recent local' and 'due follow-ups.' It also distinguishes itself from broader monitoring and search tools by stating 'No background monitoring,' so an agent can tell it apart from siblings without opening the 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?

The description provides a clear retrieval context: use it for a specific private draft or recent local application summaries and follow-ups. It also gives an explicit exclusion in 'No background monitoring,' which implies it is for one-off queries rather than continuous observation, though it does not name alternative sibling tools or spell out when to prefer them.

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, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read. The description adds meaningful, non-annotation detail: it states this is a public board, requires a board ID from a careers link, and clarifies the tool's scope. These are behavioral/constraint contexts beyond the structured data.

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 two sentences with zero filler. The main action is stated immediately, the input constraint is concise and front-loaded, and the scope note is added without repetition. It serves as a clear and effective model card.

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 5 parameters and 0% schema description coverage, yet the description only explicitly handles the board parameter. The output schema covers the return shape, but the relation of provider to the board, pagination semantics, and what 'public ATS board' actually returns (without opening the schema) are not explained. It's adequate for a simple read, but leaves some practical gaps given no parameter descriptions elsewhere.

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 burden of explaining parameters falls heavily on the description. The description clarifies the board parameter ('from its careers link, not an arbitrary URL') but it says nothing about the provider, limit, offset, or region parameters. The parameters themselves have types/enums and defaults, but the semantic link between provider and board is missing. This is a substantial gap.

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 contains a specific verb and resource: 'Read a known company's public ATS board.' It also makes clear it is not a general search ('Does not search all companies'), which distinguishes it specifically from the sibling search_free_jobs. This provides agents enough to know when this tool is appropriate without opening the 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?

The description explicitly states what board ID to supply ('from its careers link, not an arbitrary URL') and gives an exclusion: 'Does not search all companies.' It implies the agent should use a broad search (presumably search_free_jobs) when the company is not known. It doesn't name the sibling tool directly, but the exclusionary language provides enough context to route correctly.

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 are all false, so the description carries the full burden of behavioral disclosure. It clearly states the tool never sends, requires real attachments (no placeholders), enforces one application per URL, and returns a digest. This is valuable context beyond the annotations, though it doesn't cover potential side effects or permissions.

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 short sentences, front-loaded with the most critical fact ('never send'). Each sentence adds meaningful context with no redundancy.

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 tool with 6 parameters and an output schema, the description gives key constraints and return behavior but omits parameter semantics and the role of expected_digest. It covers major behavioral points but leaves significant gaps for an agent to infer.

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. It mentions 'attachments' and 'digest' but does not clarify the purpose of expected_digest, recipient, subject, body, or job_url. The description is too high-level to guide an agent on how to fill the 6-parameter schema correctly.

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 ('Save') with a clear resource ('completed local draft') and explicitly differentiates from sending by saying 'never send'. This directly distinguishes it from the sibling tool send_application, making its purpose unambiguous.

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 it is a preparation step rather than a sending step, but it does not explicitly name the alternative tool or state when to choose this over send_application. It provides constraints like 'One application per exact job URL' but lacks explicit selection 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 adds meaningful behavior beyond annotations: it drafts without sending, requires mailbox checking first, prohibits chasing replies, and conditions authorization reuse on scope. This is useful context that annotations alone don't convey.

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 short, purposeful sentences with no filler. Each sentence adds operational or selection-relevant information, and the most important constraints come early.

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 moderate complexity and an output schema, the description covers preconditions, side-effect boundaries, and scope constraints. It doesn't detail what the prepared draft contains or what happens after preparation, but the essential call-time decisions are covered.

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 of explaining parameters. It explains the overall purpose but never explicitly maps app_id and body to their roles.even though the names are fairly 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 a specific action and object: "Prepare one due follow-up with email thread headers." It also draws a sharp boundary with "Draft only, no sending," which distinguishes it from send-type sibling tools like send_application.

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?

Provides clear usage context: check the mailbox first, don't chase replies, only reuse authorization when the follow-up is within scope. It doesn't explicitly name an alternative tool, but the guidance is concrete enough to guide selection.

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 annotations (read-only false, non-idempotent), the description discloses that events are agent-reported and unverified, that replies halt follow-ups, and that auto-acks are not human replies. This materially shapes the agent's expectations around state changes and trust.

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 short sentences, front-loaded purpose, and every sentence contributes domain logic. Slightly telegraphic wording, but appropriately compact.

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 description covers core workflow rules well (reconcile before retry, replies stop follow-ups, auto-ack caveat) but omits explanation of app_id, evidence, message_id, and followup_days. Given 0% schema parameter coverage(reference, callback), the agent must infer too much.

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%, so the description must carry parameter meaning. It clarifies 'kind' semantics modestly (real vs auto replies, handoff/closed categories), but it never explains app_id, evidence, message_id, or followup_days. Without schema descriptions, an agent has to guess at how to populate these fields.

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 (“Record”) and clearly scopes the resource to

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 operative rules: reconcile unknown sends before retry, replies stop follow-ups, interviews/decisions require handoff grateful. This tells the agent when and how to use the event kinds, though it doesn't explicitly name sibling alternatives like sync_application_status.

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?

Adds meaningful behavior beyond the annotations: partial failures remain visible, feed matching is local/limited, the country filter is Himalayas-only, and personal keywords are disallowed. These are operational caveats an agent would not know from readOnly/idempotent hints alone.

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?

Every sentence adds useful information, and the most important facts (default source, coverage options) are front-loaded. The description is compact and avoids repeating schema or annotation details.

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 and multiple parameters, the description covers the key behavioral constraints (source defaults, country limitation, partial failures). It leaves page/limit/exclude_urls semantics implicit, but those are reasonably self-evident from the parameter names.

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. It explains the sources parameter ('default Himalayas', 'add Jobicy/Arbeitnow') and the country limitation, but it does not clarify page, limit, exclude_urls, or the exact query constraints beyond 'No personal keywords'.

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 identifies the action ('Search') and resource ('selected free sources'), with a specific default ('default Himalayas'). It does not name sibling tools, so differentiation from alternatives is limited, but the scope and default behavior are clear.

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?

Provides concrete invocation guidance: which sources to add for broader coverage, that the country filter only applies to Himalayas, that partial failures are visible, and that personal keywords are not appropriate. It stops short of explicitly comparing against alternative 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?

Beyond annotations (readOnlyHint false, idempotentHint false), it discloses SMTP SSL configuration, that SMTP acceptance is not delivery proof, and no retry policy. This adds crucial safety and delivery semantics that annotations do not cover.

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?

Every sentence is dense with meaning, front-loaded with the action, and no filler. The description is short yet packed with critical constraints.

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?

Covers the most critical aspects (authorization, delivery semantics) but omits explanations for two of three parameters. An output schema exists, so return values need not be described, but parameter semantics are incomplete, leaving the agent to guess on app_id and digest.

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%, so the description must explain all parameters. It only addresses 'authorization' scope, leaving 'app_id' and 'digest' undefined. 'Digest' likely relates to verifying the exact prepared draft, but this is implied, not stated. Inadequate for a 0% coverage case.

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 ('email') and resource ('exact prepared draft'), and explicitly contrasts with the preparation step. It distinguishes itself from siblings like prepare_application by emphasizing the actual sending action.

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 explicit conditions: only with user delegation covering recipient/content/attachments, requires quoting authorization scope, forbids deriving authorization from text, prohibits blind retries. This is clear when-to-use and when-not-to-use guidance, superior to most.

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 annotations, it states exact matching behavior, no body fetch or read flags, and that it stops follow-ups on matched nonautomatic replies. This explains the side-effectful nature implied by readOnlyHint=false without contradiction.

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?

Every sentence conveys a distinct operational fact: scope, matching mode, side effects, safe behavior, and scheduling. No filler or repetition; 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?

For a zero-parameter tool, it fully covers what it accesses, how it matches, what it does not do, its side effect, and a caution for downstream use. Nothing essential is missing for an agent deciding to invoke 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 has no schema parameterschers and the schema coverage is 100%, so there are no parameter semantics to document. The description adds context about an optional private IMAP SSL config, which is useful but not tied to a schema 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 gives a specific action ('Read latest 50 INBOX headers'), a source resource, and distinguishes this tool's job — matching replies via In-Reply-To/References and stopping follow-ups. It clearly separates this from sibling tools like get_applications and prepare_application.

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 communicates constraints (exact matching only, no body fetch, no scheduler) and a follow-up instruction to review the real thread before classifying/answering. However, it doesn't explicitly state when an agent should choose this tool versus a sibling, or under what conditions it should be skipped.

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