Tessera Human Design

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that by spelling out the taxonomy of results (electromagnetic, companionship, dominance, compromise) and that it reports 'who holds what', which tells the agent what the response will look like. It does not mention failure behaviour for unresolvable birth places.

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 front-loaded sentence that opens with the verb and resource before enumerating results, with no filler. The parenthetical category definitions are dense but each one earns its place by clarifying an otherwise opaque term.

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 takes on the job of describing the return value and does so thoroughly. For a nested 3-parameter tool it leaves the input side entirely to the schema, but the output side — the harder half — is well 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 only 33% — the two nested person objects carry no top-level description — yet the description says nothing about the person inputs, language selection, or the noon/uncertainty fallback. All of that semantic detail lives in the nested schema, so the description does not 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?

States a specific verb and resource ('Compares two people's charts') and enumerates exactly what the answer contains: formed channels by category, combined chart type/definition/centres, and each person's Type, Authority and Profile. This is clearly distinguishable from get_chart, which handles a single person.

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 two-person scope implies when to reach for it instead of get_chart or get_transits, and the answer contents make the fit obvious. However, it never explicitly names a sibling or states a when-not condition, so the routing is inferred rather than declared.

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, idempotent, closed-world and non-destructive, so safety needs no restating. The description adds real value beyond them by disclosing the return payload — title plus summary, full text for the richer element kinds, and linked centres/channels/gates — which matters because there is no output schema. It does not say what happens for an unrecognized or ambiguous term.

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 purpose and the accepted input vocabulary are front-loaded in the first sentence, and the second sentence is devoted entirely to what comes back. Dense but every clause carries information an agent needs.

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

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

For a simple two-parameter read tool with full schema coverage and no output schema, the description covers purpose, input vocabulary and return shape adequately. The one gap is error/ambiguity behavior for unknown or loosely matched terms, which an agent would have to discover by 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 100%, so the schema already documents both parameters and the language enum. The description still adds semantic structure beyond the examples by grouping the accepted inputs into named element categories and tying category to response depth (full text for types, authorities, profiles, definitions and basics).

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 ("Explains") and a single, well-bounded resource ("one Human Design element") and then enumerates the element kinds it accepts, each with an example. That enumeration lets an agent distinguish this glossary lookup from the chart-computing siblings without opening any 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 enumerated categories plus examples make the intended context clear: this is a definitional lookup for a single term. It does not, however, name an alternative or state when to choose compare_charts/get_chart/get_transits instead, so routing between siblings is left partly 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?

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: the ephemeris methodology (true lunar node, Design moment at 88° solar arc), historical time zone handling, the uncertainty-window behaviour, and the fact that each element carries a title plus one-line summary. These are non-obvious traits an agent could not infer from structured fields.

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 dense sentences, front-loaded with the purpose before the output inventory and methodology. The long enumeration of chart elements is justified because there is no output schema, though it is at the edge of what an agent needs to decide whether to call the 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 6-parameter, no-output-schema tool, the description supplies the missing return-value information (chart sections, activations, titles and summaries) and explains both the deterministic calculation basis and the uncertainty behaviour. Nothing needed to invoke it correctly is 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 coverage is 100% and every parameter is documented there, so the description adds little per-parameter meaning beyond restating that time matters for uncertainty. Baseline 3 applies because the schema carries the parameter burden.

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?

Opens with a specific verb+resource ('Computes a person's Human Design chart from date, time and place of birth') and then enumerates exactly what the result contains (Type, Authority, Profile, centres, channels, 26 activations). This is clearly distinct from compare_charts and get_transits without needing to open 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?

The context of use is unambiguous: single-person chart from birth data, with an explicit note that unknown/approximate birth times trigger the uncertainty listing. It does not explicitly name alternatives such as compare_charts for two people, so it stops short of full when/when-not 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 readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds useful scope context — default is 'now', time is UTC, and the answer separates transit-only channels from person-completed ones — but says nothing about result size, uncertainty handling 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 sentences, front-loaded with the core output, no filler. The trailing clause 'apart from channels the transits form on their own' is slightly tangled but still earns its place by clarifying result structure.

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 must convey what comes back, and it does: activated gates and lines, plus completed channels. Nested person input and uncertainty propagation are left entirely to the schema, which is acceptable at 75% coverage.

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 75% with detailed per-field text, so the schema does most of the work. The description reinforces the UTC convention and the 'now by default' behaviour for date/time_utc, but adds no meaning beyond that for the nested person object.

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: what gates and lines the Sun, Moon, nodes and planets activate at a moment, plus the channels completed with a person's own gates. That second clause implicitly separates it from get_chart (which would give the person's own chart), though no sibling is named outright.

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?

Says defaults (now, or a given date/time in UTC) and hints at intent with 'the usual way to read a day's influence'. But it never states when to prefer get_chart or compare_charts instead, so the choice between siblings is left to inference.

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