Nikola Dikic - Full-Stack Developer, WordPress, WooCommerce, ERP Integrations

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the description's 'Read-only' merely restates structured data. It adds genuine context that returned times are real slots and scoped to the next few weeks, but discloses nothing about result format, slot count, or failure modes.

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 zero filler; the resource is front-loaded and the usage rationale follows immediately.

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 small read-only lookup with full schema coverage, complete annotations, and no output schema, the description covers what and when adequately. Only minor gaps remain around return shape and rate/scope limits, which the annotations largely mitigate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters (days, timezone) are already fully documented in the schema. The description adds no parameter-level detail beyond what the schema provides, which is the baseline 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 names the resource precisely (free consultation slots over the next few weeks), so the agent knows this returns availability rather than booking one. The verb is implied rather than stated, but the output semantics are unambiguous and distinct from siblings like request_consultation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear directive plus rationale: call this before proposing a time so the suggestion is real rather than invented. That establishes ordering relative to a booking step, though it does not name an alternative tool or an explicit when-not-to-use condition.

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 it read-only, idempotent and non-destructive. The description adds genuinely new behavioral context: counts are computed rather than stored, so they cannot go stale — a freshness guarantee that changes how an agent should trust the values.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with no filler, and the payload of returned figures is front-loaded. Efficient for the amount of information conveyed.

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 and no parameters, the description must convey what comes back, and it does enumerate the returned metrics. Missing only guidance on when to prefer it over sibling listing tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is no parameter semantics burden. Baseline of 4 applies; the description correctly implies no input is required.

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 exactly which figures are returned (years working, projects completed, built-from-scratch count, response times), a clear resource for a tool whose name 'get_facts' alone would be opaque. It does not explicitly distinguish itself from siblings like list_projects, which return project data rather than aggregate figures.

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 call this versus the many sibling tools (list_projects, get_service, search_services, etc.). The use case of pulling aggregate stats is only implied by the enumerated figures.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description adds nothing behavioral. It does disclose the shape of the returned content (covers/excludes/projects/FAQs), which is useful given there is no output schema, but says nothing about auth, error behavior for unknown slugs, or language handling.

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?

One tight, front-loaded sentence with no filler; the content categories are enumerated efficiently. The phrasing 'the questions people ask' is slightly loose where 'FAQs' would be crisper.

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 carry the return-value burden and lists the main content sections, which is adequate for a simple two-parameter read. It is incomplete on the undocumented lang parameter and on failure modes for invalid slugs.

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%: slug is documented in the schema, but the 'lang' parameter is undocumented in both schema and description, leaving the agent guessing at accepted language values and default behavior. The description never mentions either parameter, 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?

The description names the resource ('one service') and enumerates what the response contains (coverage, exclusions, projects, FAQs), so an agent knows this is a detail lookup rather than a list. The 'one service' framing implicitly contrasts with list_services and search_services, but the verb is implied rather than stated and no sibling is named 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?

There is no when-to-use guidance, no prerequisite (e.g. that a slug must already be known), and no routing to alternatives like search_services or list_services. Usage is only weakly inferable from the phrase 'one service'.

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 establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds value beyond that by disclosing what the response contains — each route's purpose and expected response time — which is genuinely useful for a lookup tool.

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 dense sentence with the three options front-loaded and the payload (purpose + response time) stated last. The em-dash construction is slightly awkward but wastes no words.

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 contents need not be detailed, and the annotations cover safety. For a zero-param informational tool the description is sufficient, with only the explicit sibling routing left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate, and the empty schema is consistent with the description of a pure informational lookup.

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 and enumerates the three contact routes (book a call, written project description, urgent report), which maps clearly onto the sibling tools request_consultation, submit_project_inquiry, and submit_urgent_request. It is clear what the tool does, though it never explicitly names those siblings, so an agent must infer the routing.

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?

By framing the output as 'what each is for and the response time', it signals this is the orientation/routing tool to consult before choosing one of the three submission siblings. There is clear implied context but no explicit 'use this before X' or exclusion statement.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds no behavioral detail beyond that — no pagination behavior, no indication of what a project record contains, no result ordering. With annotations doing the work, the description contributes almost nothing extra.

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 no filler, and the resource statement is front-loaded before the usage guidance. It is efficient, though the first fragment is so terse it borders on under-specification rather than true conciseness.

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 four filter parameters, no required inputs, and no output schema, the description leaves too much unspecified — it never says what a project entry looks like, how results are ordered, or what the default listing returns. The agent can call it, but cannot predict the response shape.

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% and every parameter (limit, stack, still_live, from_scratch) is documented in the schema itself. The word "filterable" in the description gestures at the filtering capability but adds no semantics beyond the schema. Baseline 3 applies when the schema carries the full load.

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?

"Projects, filterable" is essentially a restatement of the tool name list_projects with no verb or scope statement. It never says it returns a list of past work/portfolio items, so the agent must infer the resource from the name alone. There is no differentiation from siblings like list_services or search_services.

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 one concrete usage scenario ("has he done X" questions) and an anti-pattern (don't guess from service descriptions), which is genuinely useful context. However, it never names or routes to the obvious alternatives (search_services, list_services, get_service), so the agent must decide on its own which tool fits.

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 cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, closed-world). The description adds the completeness guarantee ('in full') and characterizes the sibling's no-guessing behavior, but says nothing further about this tool's own behavior (e.g., volume, ordering) beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with what the tool returns, then the routing guidance. Slightly conversational phrasing ('what does he do') costs a little precision but costs no length.

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 detail is unnecessary, and the one optional parameter is documented in the schema. For a simple all-items list tool the description covers purpose, scoping, and sibling routing adequately.

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?

Only one parameter (lang) with 100% schema description coverage, so the schema already documents it. The description adds no format or defaulting detail, and the 'in full' framing mainly implies no filtering. Baseline 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?

States a specific action and scope – every service, in full – and explicitly names the sibling it must not be confused with (search_services). An agent can distinguish it from search_services without opening either 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?

Gives a concrete use case ('what does he do' / anything wanting the whole picture) and names the alternative plus the condition that selects it (a symptom-specific question). Routing is fully explicit.

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 only say readOnlyHint=false, idempotentHint=false, destructiveHint=false. The description goes well beyond that: it explains the side effect is an email with a 30-minute confirmation link, that nothing is reserved, that the slot remains available to others, and that only the recipient's click commits the booking. That is exactly the non-obvious behavior an agent needs.

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 core action, then the critical caveat. Every clause carries information, though the second sentence is dense and packs the thirty-minute validity, the click requirement, and the open-slot warning into one run-on.

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 explains the observable outcome (email sent, nothing booked, slot still open) so the agent knows what to tell the user. It does not cover failure modes such as an invalid email or a slot taken between check and request, which would round out a 7-parameter mutation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 86%, so the schema already documents nearly every parameter (including that start comes from check_availability and that email receives the confirmation). The description adds no syntax, format, or default information beyond that, so the baseline 3 applies.

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 ('Propose a booking') and immediately draws a hard boundary against what it is not ('does NOT book anything and does NOT reserve the time'). The confirmation-link mechanic makes it unmistakable from siblings like check_availability or submit_project_inquiry.

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 clear operational context: the slot stays open, the person must click within thirty minutes, and the agent should tell them to expect the email. It stops short of explicitly naming an alternative tool or a prerequisite step (e.g. call check_availability first, which only appears in the schema), so it is strong context without explicit sibling 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, covering the safety profile. The description adds meaningful behavioral context beyond those annotations by explaining what kinds of inputs are matched: symptoms, platforms, or system names, with concrete examples. It still does not describe return shape or pagination, so it is not fully exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly written sentences with no waste. The main purpose is front-loaded, and the examples that follow directly illustrate valid inputs.

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, read-only search tool with full annotations and a fully described two-parameter schema, the description is complete enough. It conveys the search intent and example inputs; no output schema exists, and 'Find services' adequately implies a list of matching services.

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%, so both parameters are already documented in the input schema. The description adds value beyond the schema by giving concrete example queries ('stock not matching the warehouse', 'NetSuite', 'failed renewals') that clarify the intended semantics of the required query 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?

States a specific verb and resource: 'Find services by what the visitor is trying to solve,' and clarifies the search scope with symptom/platform/system examples. It distinguishes itself from sibling tools like list_services and get_service by framing the input around a visitor problem, though it does not name any 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?

Provides clear context for when to use it: when you have a visitor's problem, platform, or system name expressed in plain words. It does not state when not to use it or name an alternative tool, but the usage context is unambiguous.

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 declare readOnlyHint=false and destructiveHint=false, so the mutation profile is partly covered; the description adds that it 'submits immediately' (no confirmation step, non-idempotent in practice) and that the email must be the real person's, plus a 24-hour response SLA. It stops short of stating whether a duplicate submission creates a second inquiry or what happens on failure.

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 the outcome and SLA, then the qualifying use case, then the routing rule and the consent warning. No filler or 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?

No output schema exists, yet the description tells the agent what to expect back (a reply within 24 hours, weekends included). Combined with 100% parameter coverage and explicit sibling routing, nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters (name, site, email, company, message) are already documented. The description reinforces the email constraint ('must be theirs and correct'), but adds no syntax, format, or validation detail beyond what the schema provides, so the baseline 3 applies.

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 concrete verb+resource ('Describe a project in writing and get a reply') plus the concrete outcome (reply within 24 hours, weekends included). It also draws a hard line against the sibling submit_urgent_request, so an agent can route without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative ('Use submit_urgent_request instead when a site is down or losing money now') and characterizes the qualifying work with examples: rebuild, migration, integration, second opinion. Both when-to-use and when-not-to-use are present.

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 only declare the mutation profile (not read-only, not idempotent, non-destructive). The description adds substantial non-obvious behavior: immediate submission with no confirmation email, same-day/eight-hour triage including weekends and multiple time zones, and that the reply arrives by phone or WhatsApp.

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 triage SLA, then submission behavior and the consent/phone caveat. The long symptom list is informative but slightly padded; still, every sentence carries actionable content.

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 what the tool does, how fast, how the reply comes back, and the consent prerequisite. With full schema coverage and no output schema, the remaining gap is only the absence of an explicit non-urgent alternative route.

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 schema already documents all five parameters, including the phone country-code and optional-email semantics. The description only reinforces the phone requirement ('send a real phone number'), adding little beyond 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?

Names a specific action (submit an urgent/broken-site request) and enumerates the concrete conditions that qualify it — checkout failure, hack, lockout, white screen. This is clearly distinguishable from non-urgent siblings like submit_project_inquiry or request_consultation.

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 real usage context: it is for sites broken 'now' with same-day triage, and it explicitly instructs the agent to 'ask the person before calling this' and to supply a real phone number. It doesn't explicitly name the non-urgent alternative to route to, which keeps it from 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds only that the response includes reasons ('and why'), which the output schema likely already documents; it discloses nothing extra about behavior.

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, the payload description front-loaded and the usage hint second. No filler, 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 zero-parameter read tool with full annotation coverage and an output schema, the description covers what it returns and when it is useful. The only gap is that the subject of the scope (whose offerings) is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies.

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 thing to retrieve — the set of items explicitly out of scope, plus the rationale — which is distinctive from siblings like get_facts or list_services. It stops short of naming the entity whose scope is meant (the 'him' is only implied), so an agent must infer the domain from sibling context.

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?

'Worth checking before recommending him for something' gives a concrete decision point for invoking the tool. It does not name alternatives (e.g., list_services or get_facts) or state when not to bother, so it is clear context without exclusions.

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