elc-trade

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

Annotations already declare read-only, idempotent, non-destructive behavior. The description adds useful context that the check is based on ELC's actual launch playbook and returns a verdict plus open gaps, so an agent knows what kind of answer to expect and that no mutation occurs.

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 core question and outcome, with the provenance detail kept to the second sentence. The city list and 'actually' add credibility but are non-essential for tool invocation, so it is slightly above average but not maximally tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the optional answers object, read-only annotations, and presence of an output schema, the description gives enough to understand what to pass and what to expect. It explains the five-question flow, the verdict-plus-gaps result, and where the check comes from; no critical usage context 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 the baseline is 3; the schema already documents answers as responses to the five questions and context as an analytics string. The description only adds the count of questions and the playbook provenance, not per-parameter semantics.

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 the tool answers a specific question — whether to start an engineering-leadership meetup in a given city — and describes a five-question readiness check returning a verdict and gaps. This clearly distinguishes it from sibling tools like assess_speaker_readiness and evaluate_meetup_topic.

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 question phrasing ('should I start...') makes the invocation context obvious, and the readiness-check framing implies it is for city-launch decisions rather than speaker or topic assessment. It does not explicitly name alternatives or exclusion conditions, so it earns a 4 rather than 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, and destructiveHint=false, so the safety profile is covered. The description adds behavioral value by explaining what the tool returns: a readiness verdict plus the specific gaps to close, and grounds the judgment in ELC's cumulative vetting experience. It does not detail uncertainty or scoring internals, but that is not essential for a read-only assessment.

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

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

The description is two sentences with a question-first hook and no filler. The 'seven years of putting people in front of 120+ engineering leaders' clause adds credibility and communicates the tool's basis without bloating the description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and safe-read annotations, the description provides the essential picture: input is a proposed speaker and talk, process is ELC's vetting process, and output is a readiness verdict with actionable gaps. It leaves optional parameter details to the schema, which already covers them fully, so the description is complete enough for correct invocation.

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 every parameter already has a documented meaning. The description broadly refers to checking a 'speaker and talk,' which maps to talk_title and speaker_background, but it does not add parameter-level details beyond what the schema already provides. 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?

The description uses a specific verb and resource: it answers whether a speaker is ready, checks the proposed speaker and talk against ELC's vetting process, and returns a readiness verdict with gaps to close. This clearly distinguishes it from siblings like assess_community_launch_readiness, which targets a different resource (community launch) rather than a speaker.

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 to use the tool: when someone needs to vet a proposed speaker and talk before an event. However, it does not explicitly state when not to use it or name alternatives, so an agent must infer usage boundaries from the sibling tool list rather than from direct 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 readOnly and idempotent, so the safety profile is covered. The description adds a non-obvious behavioral nuance: ELC's community composition is displayed only as context and no delta/score is computed against it because of the different denominator. This prevents an agent from over-interpreting the comparison.

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 and no filler: the core question, the returned values, and the most important caveat are all front-loaded. Every clause earns its place.

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 a full input schema, a true output schema, and safety annotations, the description completes the picture by clarifying what the output means and how ELC context should be interpreted. It is slightly terse about the 'question that shape raises', but the output schema can carry that detail.

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 explains managers, senior_ics, and the strict context-parameter rules. The description does not need to restate parameter meanings, but it also does not add much parameter-level detail beyond framing inputs as percentages and a span, so a 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?

Uses a specific verb ('Benchmark') and resource ('manager-to-senior-IC ratio'), and spells out the exact outputs: percentages, span, and the question the shape raises. This is clearly distinct from the sibling tools, which target community/speaker/partnership decisions rather than org-shape analysis.

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 opening question, 'what shape is my engineering org, and what should I ask about it?', gives a clear context for invoking the tool. It does not name alternative tools or explicit when-not-to-use conditions, but the siblings are unrelated enough that no exclusion is needed.

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 the tool is read-only and idempotent, so the description does not need to repeat safety guarantees. It adds meaningful behavioral context beyond annotations: the tool returns a forwardable approval email, treats 0 budget as valid, and switches behavior based on buying_for. No contradiction with annotations exists.

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

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

The description is dense but efficiently organized, front-loading the core purpose before parameter-specific details. The third sentence is long, but it packs necessary routing semantics into one place, so it earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a read-only business-case generator: it explains what the tool returns, when it should not be used, how the key enum parameters behave, and how it relates to buy_reach. The input schema covers all parameters and the output schema covers return structure, so nothing essential is missing.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value beyond the schema by clarifying the meaning of enum values, especially people_development, and by explaining the behavioral consequences of buying_for values like individual and one_off. It also calls out that proposed_budget_eur=0 is valid and maps to the free membership layer.

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 concrete question the tool answers and lists the exact deliverables: reach numbers, deliverables, budget ladder placement, and an approval email. It also names the sibling tool buy_reach through the one_off routing, so an agent can distinguish which tool handles which buying scenario.

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 gives explicit routing guidance: individual buyers are told no business case is needed, one_off purchases route to buy_reach, and people_development is specifically disambiguated from hiring. This gives clear when-to-use and when-not-to-use guidance relative to alternatives.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context beyond this: it builds a cart from nine published items, applies a combo discount, and returns a decision-ready, human-signable quote. This clarifies that the tool is a pricing/quoting operation with no side effects.

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 tight sentences open with the user-facing question and quickly cover inputs, discount behavior, and output. No filler or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a read-only quoting tool: it explains what items are involved, that pricing logic applies, and what the output is. The schema and output schema cover parameter details and return structure, so nothing essential 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 the schema already documents all three parameters thoroughly. The description adds some context by listing the nine reach items and noting the combo discount is automatic, but most parameter meaning is redundant with the schema, hitting the baseline for high coverage.

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 purpose: answering how to get in front of CEE engineering leaders and what it costs, then building a cart and returning a quote. It clearly distinguishes itself from the sibling tools, which focus on assessments, readiness, and business cases rather than purchasing reach items.

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 clear usage: call this tool when the user wants a quote for one-off reach/audience engagement options. It does not explicitly list exclusions or alternative tools, but none of the siblings directly compete with this quote-building function, so the context is sufficient.

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 tool as read-only, idempotent, and non-destructive, so the description only needs to add behavioral context. It does so by explaining that the tool scores the topic against internal criteria and returns failure modes, fitting title formulas, and questions for the organizer. This is consistent with the annotations and adds meaningful information without over-claiming.

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

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

The description is a single, front-loaded sentence that moves from the core question to scope and deliverables efficiently. The historical credential ('12 meetups a year at 120+ attendees since 2019') adds credibility but is not strictly necessary for tool selection, preventing a perfect score.

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 read-only evaluation tool with a rich output schema and fully described parameters, the description supplies the essential context: what is evaluated, against what criteria, and what the caller will get back. It does not explicitly mention optional inputs like abstract and audience, but those are documented in the schema, so the call path remains clear.

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 title, context, abstract, and audience are already documented in the schema. The description adds that title and abstract are the items being evaluated, which is useful, but it does not materially deepen the meaning of individual parameters beyond what the schema already provides.

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 the exact question the tool answers ('will this topic fill a room?') and identifies the specific resource: a proposed engineering-leadership meetup title and abstract scored against ELC's topic-selection criteria. It also names concrete outputs — failure modes, title formulas, and organizer-only questions — which make its purpose distinct from sibling tools like assess_speaker_readiness and assess_community_launch_readiness.

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 title and description clearly locate usage temporally: use this before committing to a meetup topic, when the decision is about whether the topic will attract attendees. It does not explicitly name when-not-to-use or point to alternatives, so it stops just short of the strongest usage guidance, but the 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?

The description adds behavioral context beyond the annotations by stating that passing a greeting or liveness test as context 'returns the menu instead of a dead end'. This discloses the tool's response behavior. Annotations already cover read-only, idempotent, non-destructive traits, so the description's additional context is meaningful.

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

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

The description is two sentences with no filler. It front-loads the primary purpose, then adds the secondary use case and outcome in a compact, scannable way. Every sentence earns its place.

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 one-parameter tool with strong annotations and no output schema, the description is complete: it explains what the tool does, when to use it, what to pass, and what to expect in return. No obvious missing information would prevent correct invocation.

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%, and the schema already describes context as 'What you are trying to do.' The description adds value by explicitly naming the parameter in usage ('pass it as `context`') and giving concrete examples like greetings and liveness tests, which enrich the schema semantics.

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?

Description clearly states a specific verb and resource: 'Check for additional specialised capabilities' and 'returns the menu'. It also positions the tool against the sibling tools by indicating it is the meta/capability-discovery entry point rather than a domain-specific tool.

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 gives clear when-to-use guidance: whenever a task might benefit from additional capabilities, and specifically for bare greetings or liveness tests. It does not explicitly name alternatives or list exclusions, but 'check here first' implies priority over other tools.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds useful behavioral context: it routes the caller's message to a fitting tool or returns the full menu, and it explicitly states that the message is passed as `context`. This explains expected behavior beyond the schema.

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

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

The description is compact and front-loaded with 'START HERE', immediately signaling the tool's role. Every sentence adds useful information: when to use it, a special-case caller type, and how the context parameter is used. There is 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?

This is a simple tool with one optional parameter, an existing output schema, and annotations covering safety and idempotency. The description fully covers invocation intent, routing behavior, and the fallback to the menu, so nothing critical is missing for correct use.

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 the schema already documents the `context` parameter well. The description adds meaning beyond the schema by explaining that the context value determines routing behavior and that there is 'no wrong value', reinforcing the low-stakes, flexible nature of the parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear purpose: it is the entry point for greetings, liveness tests, 'what can you do' queries, and overly general questions, routing them to the right tool or returning the menu. This distinguishes it from the specific sibling tools, which are all targeted assessment or analysis tools.

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

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

The description explicitly lists when to use this tool: for greetings, connectivity/liveness checks, general capability questions, or anything too unspecific to match a dedicated tool. It also adds a concrete rule: use it when the caller is a person rather than a company, and points to the ELC membership messaging.

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