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 behavioral load: it discloses the row-level pagination model and the resumption pattern (next_offset -> offset=next_offset), and it warns the caller to reuse the verdict vocabulary verbatim and not invent a 'verified'. No auth, permission, or error-mode context is given, so it stops short of 5.

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

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

The payload description is front-loaded in the first clause, followed by the verdict-filter rule and then pagination, so a reader can stop early. It is dense but every sentence adds operational information; only the parenthetical field list is mildly over-packed.

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 describe return contents, and it does so explicitly (reconciliation rows, metric flags, honesty, verdict vocabulary). Pagination is covered. What is missing is any indication of scope limits or relationship to sibling tools, which a 4-param, no-output-schema tool could reasonably state.

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%, so the description must carry the parameter burden, and it largely does: slug is scoped ('for a project'), verdict is explained with example values ('inflated', 'outdated'), and offset/limit pagination semantics are spelled out. It slightly undersells limit by implying a fixed 25-row page while the schema exposes limit as configurable.

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 and enumerates its contents (reconciliations of reported vs independent value, metric flags, emission honesty), so an agent knows exactly what it returns. It does not, however, differentiate itself from siblings like get_project_assessment or get_agent_trust_snapshot, so it lands at 4 rather than 5.

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 concrete usage for two parameters ('optional verdict filter narrows the rows', and the pagination instruction to call again with offset=next_offset), which is real guidance. But it never says when to reach for this tool versus the sibling assessment/breakdown tools, so overall guidance is implied rather than stated.

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 it does disclose meaningful behavioral facts: the record is signed, includes an attestation envelope for citation, and full=true can exceed 100K characters for deep reviews. It omits permissions/auth requirements and error behavior, but the payload-size warning is genuine context an agent needs before invoking.

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, purpose front-loaded, and the enumerated return contents are compressed into a single readable clause. The only minor cost is the dense list of returned artifacts, but nothing is redundant or 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?

No output schema exists, so the description does the work of describing return contents and the full-record variant, which it handles convincingly. The remaining gap is the undocumented slug parameter and the absence of any guidance about sibling tools that return overlapping subsets.

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%, so the description must compensate. It does explain 'full' thoroughly (adds data sources and the primary-data snapshot, much larger response), but the required 'slug' parameter is never described in either the schema or the description, leaving its format and source undocumented.

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 ('One project's assessment') and immediately scopes it to a single project, which distinguishes it from compare_projects. It enumerates the exact payload (dual scores, breakdowns, integrity level, verdict counts, findings, review_url, attestation envelope) so an agent knows precisely what it gets back.

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 explains the full=true/full=false tradeoff well, including the payload-size consequence, but never states when to pick this tool over siblings like get_integrity_verdicts, get_freedom_breakdown, or get_returns_breakdown, which appear to return sub-portions of the same data. Usage is implied by scope ('one project') rather than spelled out.

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.