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

Annotations already declare readOnly and non-destructive, and the description adds genuinely new behavior: redaction of the customer profile, deliberate omission of PII/KYC fields, and a prompt-injection warning that customer text is untrusted. It does not cover error or empty-result behavior, keeping it below 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 with no filler and the core action front-loaded. The middle clause is a dense comma-list of returned artifacts that would read better as a structured list, but nothing is wasted.

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 does well to enumerate the returned artifacts, and the security warning is valuable. However, it omits the identifier format, behavior when a ticket is missing or the pattern is violated, and any indication of payload size or pagination.

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 description never mentions ticket_id, its required status, or the 'T-\d+' format the schema enforces. The only parameter is left entirely to the pattern in the schema, so the description adds no semantic value 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?

Starts with a specific verb+resource ('Read one ticket') and enumerates the payload (same-customer transactions and history, redacted profile, deterministic assessment, source IDs, gaps). It is clearly distinct from the sibling list_tickets by emphasizing single-ticket scope, though it never names the sibling explicitly.

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 'Read one ticket' framing implies when it applies, and the negative scope ('Does not expose email, phone or KYC findings') hints at boundaries, but there is no explicit instruction on when to prefer this over list_tickets or when to follow with save_ticket_assessment.

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/openWorldHint/destructiveHint, so the 'Read-only' sentence is mostly redundant. The high-value addition is disclosing that results come from a 30-ticket sample rather than the full queue — a real behavioral limitation an agent must know before concluding a ticket doesn't exist.

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 declarative sentences, front-loaded with the operation and the caveat that most affects interpretation. Nothing wasted.

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 single-parameter read tool with annotations covering safety, the description supplies the one thing structured fields cannot: the sample-size limitation. Return shape and count aren't described, but there is no output schema and the tool is simple enough that this is a minor 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?

Schema description coverage is 0%, so the description should carry the parameter load. It mentions the default of open tickets, but that already appears in the schema's default field, and the closed/all enum values are never explained. Marginal value over the structured schema.

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 ('List tickets') and adds a meaningful scope qualifier: it draws from a 30-ticket sample, not the full queue. No sibling tool is named, so differentiation from get_ticket_context is left to inference, but the operation itself is 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 when the tool applies by noting the sample size and the default to open tickets, but it never says when to prefer get_ticket_context or what to do if the ticket in question is not in the sample. Usage is suggested rather than 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 openWorldHint=false and idempotent=true; the description adds meaningful context by stating the artifact is local and reaches no real system, which directly shapes agent expectations about side effects. It does not say whether repeated calls overwrite a prior brief, leaving the idempotency claim unexplained.

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 core action, and every clause adds information. Nothing 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?

For a simple two-parameter write tool with no output schema and clear annotations, the description covers the essentials: locality, content sourcing, and note semantics. The dangling mention of a 'target' not present in the schema and the absence of ticket_id guidance are the only 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?

Schema coverage is 0%, so the description must carry parameter meaning; it explains that notes describe the required human action, which is genuinely helpful. But ticket_id is never mentioned, and the reference to a 'target' that has no corresponding schema property risks confusing an agent about what to pass.

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 ('Write a LOCAL escalation brief') and makes the scope unambiguous by naming what it is not delivered to. It is distinguishable from save_ticket_assessment and save_response_draft by the escalation-brief framing, though the siblings themselves are never named.

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?

'Target and reasons come from the assessment' implies an ordering dependency on the assessment step, which is useful. However, it never states when to escalate versus drafting a response or KB article, nor any preconditions or 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 already declare the write/idempotent/non-destructive profile, so the marginal contribution here is the draft lifecycle claim: 'Never published automatically.' That tells the agent the write is safe and staged, which is genuinely useful context not covered by the annotations. It still omits where the draft lands and what permissions or validation apply.

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 the core action and the key constraint front-loaded; nothing is padded. The 'owner and suggested review date' clause spends words on fields the schema forbids (additionalProperties: false).

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 should say what a successful call returns (draft ID, location, status) and it does not. Required-parameter semantics are only half covered. It is adequate to attempt a call but leaves the agent guessing about the result and about the phantom owner/review-date fields.

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 carries the burden, and it only partly does: 'current-policy sources' adds real meaning for the sources array, but title and body are never characterized, and no length or cardinality guidance appears. Worse, the mentioned 'owner and suggested review date' are not actual properties, so an agent may look for parameters that cannot be supplied.

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 verb+resource pair ('Write a knowledge article DRAFT') is specific and the phrase 'Never published automatically' narrows the intent well. It does not explicitly distinguish itself from the adjacent save_response_draft sibling, and it names an 'owner and suggested review date' that are not parameters, which slightly muddies the picture.

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 statement of when to use this versus search_knowledge, save_response_draft, or the other save_* siblings. The only implicit cue is 'with current-policy sources', which hints at a precondition but states no exclusions or alternative routing.

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?

Goes well beyond the annotations by disclosing the human-review gate ('Always pending_human_review'), a validation caveat ('Limited validation is not a guarantee of accuracy'), and the absence of send/approve side effects. These are exactly the traits the readOnlyHint=false / destructiveHint=false pair can't convey. It doesn't say what happens on a duplicate ticket_id or how the returned draft is identified.

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, front-loaded sentences with no filler; the write action leads and the constraints follow. The phrasing is telegraphic in places ('Limited validation is not a guarantee of accuracy' is slightly ambiguous about what was validated), which costs a point.

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 4-required-param write tool with no output schema, the description covers safety profile, review workflow, and the critical source-quality requirement. Gaps remain around return value (is there a draft ID?) and whether it overwrites a prior draft for the same ticket.

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?

With 0% schema description coverage, the description compensates by explaining that 'sources' must be current policy source IDs (not arbitrary strings, despite the plain string array in the schema) and that customer_text and internal_notes are distinct audiences. ticket_id is left to the pattern constraint in the schema.

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 ('Write a customer reply DRAFT and separate internal notes'), and the emphasis on DRAFT plus 'does not send' clearly separates it from any send/approve action. It doesn't explicitly name the distinguishing sibling (save_kb_draft), so differentiation is inferable rather than stated.

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?

'Requires current policy source IDs' and 'Always pending_human_review' establish the precondition and the lifecycle stage for calling it, and 'Does not send or approve anything' marks the boundary. No explicit when-not or named alternative tool is given, so it stops short of full routing 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?

Annotations already declare mutation (readOnlyHint=false), non-destructive, idempotent, and closed-world behavior. The description adds useful context beyond that: revision audit history is recorded, mandatory assessment fields come from code, notes are supplemental, and ticket status is unaffected. It does not describe the return payload, but with annotations covering safety this is a strong disclosure.

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 with no filler. The main action and the most important behavioral exclusion (ticket status unchanged) are front-loaded and easy to scan.

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 low-complexity mutation tool with annotations covering safety and idempotency, the description gives enough context about audit history, code-owned mandatory fields, supplemental notes, and unchanged ticket status. Minor gaps remain around return values and exact assessment contents, but no output schema exists and the essential call context is present.

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 meaningfully clarifies that notes are supplemental and that other assessment fields are code-supplied, but it says nothing about ticket_id beyond the schema's pattern. With only two simple parameters, this is minimally adequate but not complete.

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 uses a specific verb and resource ('Write ... assessment record for a ticket') and distinguishes the effect from ticket status changes. It is clear enough to separate from sibling save_* tools, though the phrase 'real local assessment record' is slightly vague.

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?

Usage is implied by 'Write a real local assessment record for a ticket' and 'Does not change the original ticket status', but the description does not explicitly say when to choose this tool over save_response_draft, save_escalation, or save_kb_draft. The status exclusion is helpful but not a full usage guide.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that: the return shape ('source IDs and authority labels') and the scope caveat that unpublished plans are not customer policy, which affects how results should be interpreted.

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 core action and examples, then the return info, then the two caveats. Little waste, though the final clause about unpublished plans is terse enough to be slightly ambiguous.

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 two-parameter read-only search with no output schema, the description covers what it searches, what it returns (IDs and authority labels), and the historical-scope trap. Nothing critical is missing, though default values and result-size behavior are unstated.

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 both parameters. It partially does: 'query' is illustrated with example keywords, and 'include_historical' is tied to the old-handbook case. It still omits the default (false) and the 200-character limit, so the compensation is incomplete.

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 ('Search local policy and context by keywords') and seeds it with concrete example terms, so the agent knows exactly what corpus is being queried. It is clearly distinct from the ticket-oriented siblings, though it never names or contrasts them explicitly.

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?

'Old handbook requires include_historical=true' is a real conditional that tells the agent when to flip a flag, and 'unpublished plans are not customer policy' sets a scope boundary. However, there is no explicit statement of when to call this versus drafting a KB entry or escalating, so routing guidance is only implied.

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