Own Your Mind DeAI assessments

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

With no annotations, the description carries full behavioral burden. It does disclose the return shape (per-dimension score/max, total, grade, assessment level), which is useful, but says nothing about whether the call is read-only, how many slugs are allowed, cost/rate limits, or how missing or invalid slugs are handled.

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 with the axis constraint front-loaded and the output shape in the second position. No filler; only minor tightening is possible.

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?

There is no output schema and no annotations, so the description must do all the work. It partially compensates by sketching the return fields, but with an undocumented required 'slugs' parameter and no behavioral constraints, an agent still lacks everything needed to invoke it confidently.

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 description only explains 'axis' by naming its two accepted values ('freedom' or 'returns') — real value beyond the bare string schema. The required 'slugs' array, its format, and any length or validity constraints are never addressed.

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 (compare) and resource (projects) and scopes it to one axis with named values 'freedom' or 'returns'. This clearly separates it from single-project siblings like get_project_assessment, though the divergence from get_freedom_breakdown / get_returns_breakdown is left implicit.

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 phrase 'so an agent can rank them like-for-like' implies the use case (relative ranking across projects) but never states when this tool should be chosen over get_project_assessment or the per-axis breakdown tools. No exclusions or prerequisites are given.

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 disclose two useful traits: the output is observational rather than adjudicative, and it carries a `data_as_of` timestamp because the data refreshes only periodically — valuable staleness context. It stops short of any auth, rate-limit, or caching behavior, so the disclosure is partial.

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 snapshot is, followed by the freshness caveat. It is dense with domain jargon (OYM, ERC-8004, x402) but every clause carries information; the parenthetical enumeration of covered domains is the only mildly heavy element.

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?

There is no output schema, so the description must carry the return-value burden, and it does identify the shape at a high level — observations, methodology version, scope notes, and the `data_as_of` field. It stops short of describing the actual structure or units of the index, but it is close to sufficient for a zero-argument snapshot 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?

The tool takes zero parameters and the schema is empty, so there is nothing to disambiguate; the baseline for a no-param tool is 4. The description does not need to compensate for any parameter-level 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 specific resource (the latest OYM agent-trust index summary) and scopes its contents to ERC-8004 agent identity, reputation, and x402 settlement reconciliation. It is a noun phrase rather than a verb+resource construction, but an agent can tell what it returns. It also implicitly distinguishes itself from the sibling get_integrity_verdicts by insisting the output is 'observations ... never verdicts'.

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 freshness note ('refreshes only periodically') and the 'never verdicts' contrast hint at when this snapshot is appropriate versus the verdict-oriented sibling, but no explicit when-to-use, prerequisites, or named alternative are given. An agent must infer the routing decision.

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 does describe the return shape (dimensions with score/max and evidence, grade, total /100). However, it discloses nothing about access requirements, behavior for an unknown slug, or any side effects, leaving the operational profile thin.

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 that front-loads the resource and enumerates the dimensions compactly. It is efficient, though the parenthetical list makes it slightly heavy to parse.

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?

Because there is no output schema, the description usefully explains the returned fields, and for a one-parameter read tool that covers most of the gap. Still missing are the meaning of the required slug argument and any routing guidance relative to sibling assessment 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?

Schema description coverage is 0% and the description never mentions the single 'slug' parameter at all, so an agent gets no explanation of what identifier is expected. With one undocumented parameter the description fails to compensate for the schema 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 specific resource (a project's 6-dimension Freedom score) and enumerates the exact dimensions returned, so an agent knows precisely what this tool produces. It is clearly distinguishable from get_returns_breakdown and compare_projects by resource, though it never explicitly contrasts itself with them.

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 you call this to fetch a project's freedom score, but there is no statement of when to prefer it over get_project_assessment or compare_projects, nor any prerequisites. No exclusions or alternatives are given.

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 well: it discloses the shape of the returned data and, notably, the semantics of the verdict vocabulary and `_rule` verbatim, warning the caller to report 'not-assessed' honestly and never invent 'verified'. It does not mention auth, pagination, or empty-result behavior, keeping it 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 before the reporting caution. Dense but each clause earns its place; the parenthetical enumeration is efficient rather than padded.

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 or annotations, the description usefully characterizes the returned content and its semantics. However, it leaves the required `slug` parameter undefined, which an agent must know in order to invoke the tool correctly.

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

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

Schema description coverage is 0% and the sole parameter `slug` is undocumented in both schema and description. The phrase 'for a project' weakly implies the slug identifies a project, but no format or sourcing guidance is given, so the description 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 a specific resource — 'every claim we checked for a project against independent data' — and enumerates the concrete contents (reconciliations, metric flags, emission honesty). It is clearly distinguishable from siblings like compare_projects or get_project_assessment, though it never names them explicitly and the verb ('get') is only implied by the name.

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 infers this is the retrieval tool for integrity verdicts on a single project. There is no statement of when to prefer it over compare_projects or get_project_assessment, and no prerequisites or exclusions are given.

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. It usefully discloses that the record is signed (substrate_hash + per-project ed25519 signature), which is real behavioral value. However, it says nothing about read-only semantics, permiss requirements, behavior when the slug is unknown, or rate limits.

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, but it is dense with domain jargon ('substrate record', 'attestation envelope', 'integrity reconciliations') that could obscure rather than clarify. No wasted sentences, but the compression trades off 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?

There is no output schema, and the description does describe the return contents reasonably well. But it omits how to source the required slug and when to prefer this over the granular sibling tools, leaving meaningful gaps for an agent.

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

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

Schema description coverage is 0% and the single 'slug' parameter carries no description. The description adds no meaning about what a slug is or how to obtain one (e.g., via list_projects), so it fails to compensate for the undocumented 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 ('get') and resource ('full signed substrate record for one project') and enumerates the contents (dual scores, breakdowns, integrity reconciliations, attestation envelope). It implicitly positions itself as the comprehensive record relative to the narrower breakdown siblings, though it never names them.

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 explicit when-to-use guidance or when-not-to-use, and no alternatives are named despite siblings like get_freedom_breakdown, get_returns_breakdown, and get_integrity_verdicts covering subsets of this data. The agent must infer that this is the aggregate version rather than a targeted call.

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 burden. It does disclose the return structure (five named dimensions with score/max and evidence, plus grade and total /100), which is genuine behavioral context, but it says nothing about error/not-found handling, whether scores are cached or computed live, or cost/latency.

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 that front-loads the resource and enumerates the payload contents without filler. It is efficient, though the parenthetical dimension list makes it slightly list-heavy rather than task-oriented.

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 compensates by outlining the return payload, which is its strongest contribution. It remains incomplete on the input side (slug meaning/format) and on failure behavior, but for a one-parameter read tool it is close to adequate.

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

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

Schema description coverage is 0% and the sole parameter 'slug' is undocumented in the schema. The description only implies it via 'for a project'; it never states that slug is a project identifier, its format, or where to obtain one.

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 verb (implicitly retrieves) and resource (the 5-dimension Returns score for a project), and enumerates exactly what the score covers. It does not, however, distinguish itself from structurally similar siblings such as get_freedom_breakdown or get_project_assessment, leaving an agent to infer the difference from the names 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?

There is no when-to-use statement, no prerequisite (e.g. needing a valid project slug), and no mention of alternatives like compare_projects or get_project_assessment. Usage is only inferable from the tool 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 behavioral burden. It does disclose the key scope constraint (summaries, not full records) and flags the `_rule` honesty-contract field. However, for a 'list every' tool it says nothing about pagination, result size limits, ordering, or auth, which are the traits an agent most needs here.

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

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

Four short sentences, front-loaded with the primary purpose, then filters, then the sibling routing hint, then the contract note. No sentence 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?

There is no output schema, so the description must cover return values, and it does state what a summary contains and that the full record lives elsewhere. Pagination/ordering behavior for an unbounded list is the one material omission.

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

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

Schema description coverage is 0% and the schema declares no enums, so the description compensates meaningfully by enumerating all seven category values. Status is only given as 'e.g. active', leaving its full value set unknown, so it falls short of the full 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?

Specific verb ('List') plus resource ('assessed decentralised AI project') with the exact payload named (dual scores, grades, assessment level). It also distinguishes itself from the sibling get_project_assessment by stating that this tool returns summaries only.

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 ('call get_project_assessment for the full record') and the condition that selects it ('Returns summaries only'). Also frames the two optional filters as optional, so the agent knows it can call with no arguments.

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