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

With no annotations supplied, the description carries the full burden and does reasonably well: it discloses that nothing executes, no network connection occurs, and the output is a graded checklist rather than a certification. This preempts the main misuse risk (treating the score as a safety guarantee). It does not mention input size limits or failure behavior on malformed JSON, which are the remaining behavioral gaps.

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 purpose before the caveats. The phrasing is fragmentary but every sentence adds information; nothing is redundant. Slightly more polish in wording would help readability without lengthening 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?

An output schema exists, so return-value details are correctly omitted, and the negative scoping (no execution, no live connection, not a certification) covers the key behavioral question for a single-parameter tool. Only minor details, such as handling of malformed input or expected size, are absent.

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, and it does by defining the expected shape: a JSON list of objects with 'name' and 'description'. The one weakness is that the schema types tools_json as a string while the description calls it a 'JSON list', leaving ambiguity about whether the agent should pass a serialized string or an array.

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 the resource (an MCP server's tool list) and the operation (a static security checklist audit), so an agent knows exactly what it produces. It is distinguishable from all siblings, which are unrelated utility tools (password, currency, repo, URL checks), 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?

It sets clear boundaries on use: 'Nothing is run and nothing connects to a live server' and the result is 'a checklist score, not a safety certification.' That tells an agent when this is appropriate (static review of tool metadata) and what not to expect from it. What's missing is an explicit statement of when to prefer this over any alternative, but no comparable sibling exists.

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?

No annotations are provided, so the description carries the full behavioral burden, and it delivers meaningfully: it discloses the k-anonymity mechanism, exactly what data leaves the system (first 5 SHA-1 characters), and that the password and full hash are never sent, stored, or logged. It does not cover rate limits, offline/failure behavior, or result semantics beyond the count, 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?

Two short blocks: the purpose sentence first, then the privacy note. Every sentence earns its place, and the privacy disclosure is exactly the kind of information an agent needs before passing a secret into a tool.

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 an output schema present, the description covers purpose and the critical privacy behavior. The main remaining gap is a lack of explicit guidance on when to prefer it over the sibling password tools, but nothing essential for correct invocation 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 0%, so the description must compensate. It does convey that the parameter is a plaintext password and that hashing is handled internally, but it does not state format constraints such as length, encoding, or whether an already-hashed value is accepted. Baseline-adjacent with a useful hint but 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: count how many times a password appeared in known data breaches. This is clearly distinguishable from sibling tools like password_strength and generate_password, and an agent can tell what it returns 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 implies usage (check whether a password has been exposed) but never explicitly says when to use this versus password_strength or generate_password, nor does it state any preconditions such as requiring a plaintext password. Usage is inferable but not guided.

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?

With no annotations, the description carries the full burden and does substantial work: it discloses the SSRF guard, the globally-routable-only restriction, the five-redirect cap, HEAD-only requests, and that nothing is downloaded or submitted. It does not cover timeouts, rate limits, or authentication requirements, which leaves room above a 4.

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?

Front-loaded with the purpose, then grouped into guard behavior, request behavior, and error semantics. Every sentence contributes a distinct operational fact with no repetition.

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 one-parameter tool with an output schema, this covers nearly everything an agent needs, including the crucial clarification that `reachable: false` is a successful check result rather than a failure. The remaining gap is URL format and timeout behavior.

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% for the single `url` parameter, so the description must compensate. It adds the important constraint that only globally routable addresses may be fetched, but never states whether a scheme is required or which schemes are accepted, leaving the most basic input-format question unanswered.

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: check whether a URL is reachable and what status it returns. No sibling overlaps this capability (the siblings are password, expense, currency, repo, and time tools), so there is no ambiguity to resolve.

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 only implied: an agent can infer this is for verifying URL reachability, but there is no explicit statement of when to prefer it over another approach and no exclusions. There are no close alternatives among the siblings, which softens the gap but does not eliminate it.

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?

With zero annotation coverage the description carries the full behavioral burden, and it does disclose several useful traits beyond the schema: no API key required, upstream source exchangerate-api.com, indicative (non-authoritative) rates, a 'not financial advice' caveat, and a 5-minute in-memory cache. However, it omits what happens on an invalid or unsupported currency code, whether unsupported pairs are rejected or approximated, and whether any rate limiting applies to callers.

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, and the core action is front-loaded ahead of the provenance and caveat details. The mid-sentence line breaks are cosmetic noise but do not impair readability.

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?

An output schema exists, so return values needn't be explained, and the caching and disclaimer context is genuinely helpful for a rate lookup. What is missing for a three-required-parameter conversion tool with no schema descriptions is any specification of currency code format or amount constraints, which an agent needs to invoke it correctly on the first try.

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 all three parameters are required with no titles beyond bare names, so the description is the only source of meaning. It says nothing about expected currency code format (ISO 4217 like 'USD' vs a name), casing, or whether amount may be negative or zero. It only indirectly implies the parameters by describing the operation.

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 verb ('Convert') and resource ('an amount between currencies') plus the mechanism ('a free no-key rate API'), so the operation is unambiguous. No sibling tool deals with currency, so no explicit differentiation is needed or provided, which caps it just below the top mark.

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 the purpose rather than stated: there is no explicit 'use this when...' guidance, no mention of when a different tool would be preferable, and no prerequisites called out. Given the sibling set contains nothing adjacent to currency conversion, the omission is low-risk but still a gap.

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?

With no annotations supplied, the description carries the full burden and does disclose meaningful behavior: the password is generated on the server, returned to the caller, and never stored or transmitted elsewhere. It also discloses input clamping ('Length is clamped to 8-64'), which tells the agent how out-of-range values are handled. It stops short of describing the character-set/entropy guarantees or what happens if include_symbols makes generation impossible, so not 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?

The core action is front-loaded in the first sentence, and the following sentences add non-redundant behavioral context. Slightly padded by line breaks, but no wasted wording.

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?

An output schema exists, so return values need not be explained, and for a simple two-parameter generator the description covers what is generated, where it is generated, whether it is persisted, and the input bounds. The only residual gap is include_symbols semantics, which is minor at this complexity.

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 does add real meaning for 'length' by declaring the 8-64 clamp that the schema does not state, but it says nothing about 'include_symbols' — the parameter that most affects the output's character set. Partial compensation for a two-parameter tool.

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 ('Generate a random password') plus the mechanism ('secrets module'), which unambiguously separates it from siblings like check_password_breach and password_strength. An agent can pick this tool 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?

Usage is implied by the description (produce a fresh random password, generated server-side rather than stored), but there is no explicit when-to-use/when-not guidance and no routing to siblings such as password_strength for validating an existing password. Adequate but leaves the agent to infer the workflow.

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?

With no annotations supplied, the description carries the full burden and does well on the important traits: it discloses the auth model (no token required) and a real behavioral limit (private repos are invisible to the public API by design). It does not cover error behavior for a nonexistent username or rate limiting, which is why it falls short of 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, front-loaded with the resource and its contents, followed immediately by the data-visibility constraint. Nothing is repeated and every clause adds information an agent would otherwise have to guess.

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 one-parameter, read-oriented lookup with an output schema already documenting returns, this covers purpose, scope, and visibility limits adequately. The remaining gap is edge-case behavior (nonexistent user, rate limits) and parameter format, which is minor given the tool's simplicity.

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% for the single 'username' parameter, so the description would need to compensate. It does not add format detail such as whether this is the login handle versus display name, case sensitivity, or whether a URL is accepted, though the parameter name itself is largely self-documenting.

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 (a GitHub user) and enumerates exactly what the summary contains: profile, repo count, total stars across public repos, and most-used languages. That is concrete enough that an agent can distinguish it from repo-scoped siblings like repo_health and repo_compare without opening a 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?

Scope is stated ('public data only, no token'), which implies when the tool is applicable, but there is no explicit when-to-use guidance or named alternative (e.g., 'use repo_health for a single repository'). The agent must infer that this is the user-level overview tool rather than a repo-level one.

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?

With no annotations, the description carries the full behavioral burden and does meaningful work: it reveals the scoring rubric (five named criteria), discloses that the password is scored locally and never transmitted, and sets expectations that the result is advisory rather than a security guarantee. What is missing is only what the improvement explanation contains, which the output schema already covers.

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 outcome, followed by the rubric and then the caveat. Every sentence adds information not present in the structured fields, and nothing is 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 one-parameter tool with an output schema, the description covers scoring logic, privacy handling, and the interpretation caveat. The only gap is the absence of explicit sibling routing, which is minor given how distinct this tool's function is.

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% and the single parameter 'password' is a bare string with no constraints in the schema. The description compensates for the most important semantic point by stating the value is processed locally and never sent anywhere, but adds nothing about length limits, encoding, or whether the plaintext is echoed back.

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: 'Score a password 0-5 and explain how to improve it.' It is immediately distinguishable from the siblings check_password_breach (breach lookup) and generate_password (creation), so an agent can route correctly 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?

Usage is only implied: the tool is presumably for evaluating a password the user already has, and the caveat 'strength hint, not a guarantee' hints at when its result is insufficient. It never explicitly says when to prefer check_password_breach or generate_password instead, nor any prerequisites, so the agent must infer the 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?

No annotations are supplied, so the description carries the full behavioral burden. It hints that only public repositories are accepted but says nothing about which health signals are compared, what happens with nonexistent or private repos, rate limits, or whether the two repos must be related.

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 tight sentence with no filler and the key constraint ('two public repositories') front-loaded. Its brevity is efficient in form, though it borders on under-specification rather than 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?

An output schema exists, so return values need not be described. But for a four-parameter comparison tool with zero annotation and zero schema-description coverage, the description omits comparison dimensions, error behavior, and parameter pairing semantics, leaving real 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 description coverage is 0%, with four required parameters documented only by bare titles like 'Owner1' and 'Repo1'. The description does not explain that the parameters form two owner/repo pairs, nor any format expectations (URL vs slug, case sensitivity), so it fails to compensate for the coverage 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?

Names a specific verb ('health comparison') and resource ('two public GitHub repositories') in a single clear phrase. The word 'two' and 'side-by-side' implicitly separates it from the sibling repo_health, which handles a single repo, though that sibling is 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?

No statement of when to pick this over repo_health, no prerequisites, no exclusions. An agent must infer that repo_health is the single-repo alternative and that private repositories are out of scope from the word 'public' alone.

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?

With no annotations, the description carries the behavioral burden, and it does disclose one important trait: extra calls (languages, PRs) may fail and return null rather than failing the whole check. It does not mention authentication needs, rate limits, or that PR counting is capped at the first 100 open PRs in a way that could undercount — actually the cap is stated, but the consequence (truncated counts) is not spelled out.

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?

Roughly three sentences with the core purpose front-loaded and the failure-mode caveat last. 'Plus upgrades' is slightly awkward phrasing but no sentence 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?

An output schema exists, so return values need not be explained, and the failure semantics are covered. Missing pieces for a tool that makes multiple GitHub API sub-calls are auth expectations and rate-limit behavior, which an agent would want before calling.

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% — 'owner' and 'repo' are bare strings with no descriptions. The description compensates only partially by restricting the repo to public GitHub repositories; it says nothing about owner login format (user vs org) or case sensitivity. Adequate but not fully compensating for the coverage 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?

States a specific verb (health summary) and resource (a public GitHub repository), plus the included data (top languages by bytes, open PR count). It is clearly not repo_compare or github_user_summary, though it never names a 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 'PUBLIC' qualifier implicitly tells the agent this tool is unsuitable for private repos, which is useful scoping. However, there is no explicit when-to-use guidance or routing to repo_compare for comparison tasks; usage must be inferred from the name.

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?

With no annotations, the description carries the full disclosure burden and does meaningful work: it defines the sign convention, states the invariant that values must sum to zero, and specifies integer poisha as the money unit. It stops short of saying what happens if the invariant is violated (error vs. silent normalization) or how ties in the minimal-payment set are resolved.

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 clauses with the core action front-loaded, then the input contract and the unit convention in dependency order. Nothing is repeated and nothing is 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?

Output schema exists, so return values need not be described, and the description covers the input semantics and the key invariant for a one-parameter computational tool. The remaining gap is failure behavior when the sum is non-zero, which matters for a tool that hard-constrains its input.

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% and the single parameter is a nested free-form object, so the description must compensate — and it does, explaining that keys are people and values are signed net positions in integer poisha. It leaves a minor ambiguity: the schema types values as 'number' while the text says integer poisha, so the agent is not told whether floats are rejected or rounded.

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 plus the optimization goal: 'Simplify any set of balances into the fewest payments.' An agent can tell this is a netting/settlement computation rather than the arithmetic in split_expense, though the description never names that 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?

Usage is implied by the input contract ('balances maps each person to what they are owed (+) or owe (-); the values must sum to zero'), which effectively tells the agent the precondition for calling it. There is no explicit when-to-use, when-not-to-use, or pointer to an alternative, so the routing signal is indirect.

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?

With no annotations supplied, the description carries the full burden, and it does disclose two real behaviors: remainder poisha are allocated to the first members so shares sum exactly, and custom shares that do not sum to the total produce a validation error. It does not state whether the expense is persisted/mutated, whether it requires prior setup, or anything about side effects, so a mutation-vs-pure-computation question is left open.

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 paragraphs, each front-loading its mode, with no filler sentences. The only minor friction is the unexplained "poisha" term and the line break that splits the equal-split sentence mid-thought.

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?

An output schema exists, so return values need not be explained, and the splitting arithmetic is well covered. Still, for a four-parameter tool with 0% schema coverage and no annotations, the undefined paid_by and the unspecified currency/units of total_amount are meaningful gaps an agent would have to guess at.

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 all four parameters, and it only partly does: it explains the interaction between members and custom_shares and the exact-sum constraint, but never defines paid_by (payer identity semantics) or the unit of total_amount beyond the unexplained word "poisha".

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?

"Split an expense and simplify who owes whom" gives a specific verb and resource, and the two named modes (equal vs custom) clarify scope. It does not differentiate itself from the sibling settle_balances, which plausibly also deals with who-owes-whom, so an agent must infer the boundary.

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 effectively distinguishes two invocation modes (equal split vs custom_shares) and states the failure condition for the custom path, which is useful routing guidance at the parameter level. However, it never says when to choose this tool over settle_balances or whether the expense is persisted, leaving the sibling relationship to inference.

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?

With no annotations, the description carries the full disclosure burden. It does add genuinely non-obvious behavior by revealing that the response also contains UTC and Asia/Dhaka values alongside the requested zone, but it says nothing about how invalid or misspelled timezone names are handled or what the failure mode looks like.

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, front-loaded with what the tool returns before the format examples. Every element earns its place; the example list is the most valuable part for callers and nothing is 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 one-parameter read-only utility with an output schema already defining return values, this is nearly sufficient: purpose, format and examples are all present. The only meaningful gap is error behavior for invalid timezone identifiers, which the annotation-free description could have 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 schema says only 'timezone_name: string'. The description compensates well for a single parameter by naming the format ('IANA timezone') and giving four concrete valid examples spanning Asia/Dhaka, Asia/Kolkata, Europe/London and America/New_York, which is enough for an agent to construct a correct value.

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 and scope: 'Current time in a given IANA timezone', and even enumerates the extra values returned (UTC and Asia/Dhaka). No sibling tool covers time lookup, so there is nothing to confuse it with, and an agent can select it from the name plus this sentence alone.

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 only implied: the agent can infer it is the tool for 'what time is it in X'. There is no explicit when-to-use framing, no statement of when not to use it, and no prerequisite such as requiring a valid IANA identifier rather than a city name or offset.

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